© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 322
    Prev
    Next
    INDEX
    Explanations

    under

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ats
    -0.27
    lastic
    -0.24
    ORS
    -0.24
     ever
    -0.23
    utschen
    -0.23
    ç»IJ
    -0.23
    åĩī
    -0.23
    QA
    -0.23
     Erg
    -0.23
    _UNIQUE
    -0.23
    POSITIVE LOGITS
    ç§ijåѦåıijå±ķ
    0.27
    borg
    0.25
    iah
    0.24
     fst
    0.24
    srv
    0.24
    橱
    0.24
    -basket
    0.23
     ÐijÑĢ
    0.23
    .breakpoints
    0.23
    'order
    0.23
    Activations Density 0.011%

    No Known Activations