© 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. 25-TRANSCODER-HP
    7. 107850
    Prev
    Next
    INDEX
    Explanations

    Related to eyes/looking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calls
    -0.33
    call
    -0.32
     calling
    -0.32
    calling
    -0.31
     discussions
    -0.31
     Discussions
    -0.30
    åij¼åı«
    -0.30
    _calls
    -0.28
    Calls
    -0.28
    .call
    -0.28
    POSITIVE LOGITS
    æĬ¬å¤´
    0.38
    æĬ¬èµ·å¤´
    0.36
    åľ°çľĭçĿĢ
    0.34
    çľĭåIJij
    0.32
    çĿģå¼Ģ
    0.31
     eyes
    0.31
    look
    0.31
    çĿģ
    0.31
     eyed
    0.30
     eye
    0.30
    Activations Density 0.958%

    No Known Activations