© 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. 24-TRANSCODER-HP
    7. 149624
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oversh
    -0.26
    -encoded
    -0.26
    òa
    -0.24
    ä¸į管
    -0.24
    kbd
    -0.24
    忽çķ¥
    -0.24
    缬
    -0.23
    é²ľ
    -0.23
     specials
    -0.23
    _EOL
    -0.23
    POSITIVE LOGITS
    isk
    0.27
    iske
    0.26
    Having
    0.25
     bask
    0.25
    ippers
    0.25
    lu
    0.25
     ATTRIBUTE
    0.24
    lt
    0.24
     Provision
    0.24
     Having
    0.24
    Activations Density 0.147%

    No Known Activations

    This feature has no known activations.