© 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. 31-TRANSCODER-HP
    7. 19430
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩİ
    -0.29
    éĶħ
    -0.26
    æŃ¢
    -0.26
    -holder
    -0.25
    CASE
    -0.25
    itas
    -0.25
    Ñĥгл
    -0.24
    åĤ¬çĶŁ
    -0.24
    opro
    -0.24
    è¿ĩçļĦ
    -0.24
    POSITIVE LOGITS
     ride
    0.26
     sight
    0.25
    ä¹ĥ
    0.25
    ride
    0.25
    è¨Ĥ
    0.25
    ÑĢид
    0.24
    ç»ıå¼Ģ
    0.24
    >Action
    0.24
    ders
    0.24
    å¾·å°Ķ
    0.23
    Activations Density 6.073%

    No Known Activations

    This feature has no known activations.