© 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. 33-TRANSCODER-HP
    7. 53180
    Prev
    Next
    INDEX
    Explanations

    uncommon or random sequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    失æķĪ
    -0.28
    .bundle
    -0.24
    å·¥ä½ľä»»åĬ¡
    -0.24
    fork
    -0.24
    ä»»åĬ¡
    -0.23
    åıĹçģ¾
    -0.23
    æ·±åİļ
    -0.23
    (Packet
    -0.23
    icip
    -0.23
    åİŁæłĩé¢ĺ
    -0.23
    POSITIVE LOGITS
    omid
    0.28
    ensa
    0.28
     bias
    0.27
    QM
    0.26
    em
    0.26
    ypi
    0.26
    念
    0.25
    ưỡng
    0.25
    Disclosure
    0.25
    ek
    0.25
    Activations Density 0.007%

    No Known Activations