© 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. 96261
    Prev
    Next
    INDEX
    Explanations

    :

    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
    whether
    -0.28
    ][(
    -0.28
     Tasks
    -0.27
    antee
    -0.27
     æĺ¯åIJ¦
    -0.26
     whether
    -0.26
    ç½ijç«Ļé¦ĸ页
    -0.26
    .arraycopy
    -0.25
     FORE
    -0.25
    task
    -0.25
    POSITIVE LOGITS
    Who
    0.41
     Who
    0.39
    who
    0.35
     who
    0.35
    è°ģ
    0.33
    åĪĨç±»
    0.33
     Wh
    0.32
    ä½ľä¸º
    0.30
     How
    0.29
    è¯Ń
    0.28
    Activations Density 1.038%

    No Known Activations