© 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. 30-TRANSCODER-HP
    7. 96292
    Prev
    Next
    INDEX
    Explanations

    therm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foul
    -0.27
    |[
    -0.25
    iences
    -0.25
     Тем
    -0.25
     BA
    -0.24
     Bras
    -0.24
    TECT
    -0.24
     telefone
    -0.24
    ãĤĴæĦŁãģĺ
    -0.24
    ])(
    -0.23
    POSITIVE LOGITS
    åł¡
    0.29
    QUERY
    0.26
    cki
    0.24
    åĺİ
    0.24
    /gallery
    0.24
    éĥ½çŁ¥éģĵ
    0.24
     accom
    0.24
    å¤Ħå¤Ħéķ¿
    0.24
    åģļå¾Ĺ
    0.23
    KeyName
    0.23
    Activations Density 0.005%

    No Known Activations