© 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. 35-TRANSCODER-HP
    7. 39721
    Prev
    Next
    INDEX
    Explanations

    code and technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Di
    -0.32
     proud
    -0.30
     di
    -0.29
    URA
    -0.28
    _di
    -0.26
    along
    -0.25
    ju
    -0.25
    çļĦç¡®
    -0.25
    éŨ
    -0.25
     pride
    -0.25
    POSITIVE LOGITS
    itarian
    0.31
    or
    0.30
    erm
    0.29
    åĵĻ
    0.28
    olle
    0.27
    ieder
    0.27
    conciliation
    0.27
    ainless
    0.26
    rarian
    0.26
    ermo
    0.25
    Activations Density 0.330%

    No Known Activations