© 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. 19315
    Prev
    Next
    INDEX
    Explanations

    technical writing and arguments

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¼ļè°Ī
    -0.28
    å¿«éĢŁåıijå±ķ
    -0.28
    路线
    -0.27
     Sav
    -0.27
    fleet
    -0.27
    æł¹
    -0.26
    mtree
    -0.26
    ç»ıæµİ
    -0.26
    ниÑĨа
    -0.25
     roots
    -0.25
    POSITIVE LOGITS
    aan
    0.29
    itational
    0.28
     punch
    0.27
    çĽĸ
    0.27
    ToWorld
    0.26
    edException
    0.25
    ä¼
    0.25
    aad
    0.24
    itan
    0.24
     Stevenson
    0.24
    Activations Density 1.971%

    No Known Activations