© 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. 14-TRANSCODER-HP
    7. 40919
    Prev
    Next
    INDEX
    Explanations

    Formal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abı
    -0.28
    èĢĻ
    -0.26
     belts
    -0.26
    夯
    -0.26
     Limits
    -0.26
     reassuring
    -0.25
    itim
    -0.25
    QM
    -0.25
     Siri
    -0.25
     confirm
    -0.25
    POSITIVE LOGITS
    ude
    0.28
    trace
    0.28
    ç¿»
    0.27
    uer
    0.27
     temporarily
    0.27
    ischen
    0.27
    èĴĻ
    0.27
    åĮħ
    0.26
     temporary
    0.26
    rer
    0.26
    Activations Density 0.511%

    No Known Activations