© 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. 19-TRANSCODER-HP
    7. 7732
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¸Ĭ
    -0.27
    doch
    -0.27
     lowercase
    -0.27
    alink
    -0.27
    irror
    -0.26
    avian
    -0.25
    ipeg
    -0.25
    å¾Ĵ
    -0.25
    _NS
    -0.25
    egie
    -0.24
    POSITIVE LOGITS
    -feature
    0.26
    åħµåĻ¨
    0.26
    ram
    0.26
    代
    0.25
     Custom
    0.24
    lac
    0.24
    èĦļ
    0.24
    ati
    0.24
    è¨ĺ
    0.24
    çĻ
    0.24
    Activations Density 0.232%

    No Known Activations

    This feature has no known activations.