© 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. 12-TRANSCODER-HP
    7. 22789
    Prev
    Next
    INDEX
    Explanations

    _pref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.28
    ))^
    -0.27
     closures
    -0.25
    约æĿŁ
    -0.25
    liche
    -0.25
    aki
    -0.25
    ä¸Ģéĺµ
    -0.24
    ä¸Ńåħ³
    -0.24
    åł¡åŀĴ
    -0.24
    /component
    -0.24
    POSITIVE LOGITS
    çŁ£
    0.26
     pumps
    0.25
    istream
    0.24
     Pump
    0.24
    -Headers
    0.24
     pump
    0.23
     Ñģоб
    0.23
     Featuring
    0.23
    _periods
    0.23
     Strait
    0.23
    Activations Density 0.000%

    No Known Activations