© 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. 32-TRANSCODER-HP
    7. 43776
    Prev
    Next
    INDEX
    Explanations

    personal narratives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _enter
    -0.27
     Beat
    -0.27
    ek
    -0.26
    needle
    -0.26
    akter
    -0.26
    èĬ¥
    -0.26
     xrange
    -0.26
    ondon
    -0.26
    mere
    -0.26
     sponsor
    -0.25
    POSITIVE LOGITS
     along
    0.29
     paired
    0.27
    along
    0.27
     worked
    0.26
     dziaÅĤ
    0.26
    ivos
    0.26
    arios
    0.25
    éķ¿æ±Ł
    0.25
    rary
    0.25
     driving
    0.24
    Activations Density 0.016%

    No Known Activations