© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 22303
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.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¸ħ
    -0.28
    éľģ
    -0.26
    abric
    -0.26
    DOMNode
    -0.25
    poi
    -0.25
    åĩ¶
    -0.24
    rett
    -0.24
    fre
    -0.24
    ault
    -0.24
     spot
    -0.23
    POSITIVE LOGITS
    ingles
    0.30
    ovsky
    0.28
    ensem
    0.28
     indiv
    0.28
    hee
    0.27
    inger
    0.26
    ingle
    0.26
    ingular
    0.25
    insky
    0.25
    çŁ
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.