© 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. 31-TRANSCODER-HP
    7. 19845
    Prev
    Next
    INDEX
    Explanations

    follow

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    æIJŀå®ļ
    -0.26
    è°İè¨Ģ
    -0.26
    horn
    -0.25
     dissert
    -0.25
    çŀĢ
    -0.24
    ä¸įæĢķ
    -0.24
    æĥ³èµ·æĿ¥
    -0.24
    ->$
    -0.24
     "*.
    -0.23
     slam
    -0.23
    POSITIVE LOGITS
     follow
    1.09
     follows
    1.05
     Follow
    0.94
    follow
    0.93
     following
    0.92
    Follow
    0.90
     FOLLOW
    0.86
     Following
    0.85
    following
    0.83
    Following
    0.83
    Activations Density 15.568%

    No Known Activations