© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 24202
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç¡ķ
    -0.27
     Episodes
    -0.26
     rubber
    -0.24
    èĶij
    -0.24
     Located
    -0.24
    림
    -0.24
    vents
    -0.23
    icamente
    -0.23
    :description
    -0.23
     ----------------------------------------------------------------------------
    -0.23
    POSITIVE LOGITS
    æĺĵäºİ
    0.26
    ObjectContext
    0.25
    ForKey
    0.24
    交æİ¥
    0.24
    èĸ°
    0.24
    è¿ĩçļĦ
    0.24
    ammers
    0.24
    ç»ĨåĮĸ
    0.24
    è§ĦåĪĴ设计
    0.24
    dh
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.