© 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. 30-TRANSCODER-HP
    7. 95789
    Prev
    Next
    INDEX
    Explanations

    history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cope
    -0.32
    å±ģ
    -0.29
    Ãłng
    -0.26
    å¿ħä¸įåı¯
    -0.26
    ’Ãł
    -0.26
    udit
    -0.26
    æŧ
    -0.26
    iced
    -0.26
     lei
    -0.25
    ;base
    -0.25
    POSITIVE LOGITS
     gente
    0.28
     Rough
    0.27
     prox
    0.26
     exist
    0.26
     relatively
    0.26
    å¼Ģåıij
    0.25
    ä¸į解
    0.24
    Ñħодим
    0.24
     accelerating
    0.24
     khoảng
    0.24
    Activations Density 0.884%

    No Known Activations