© 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. 96451
    Prev
    Next
    INDEX
    Explanations

    verbs about viewing

    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
     Shirt
    -0.26
    ãĤįãģĨ
    -0.26
    illi
    -0.25
     crisp
    -0.25
    “You
    -0.25
    离
    -0.24
    ishes
    -0.24
    /platform
    -0.24
    inus
    -0.23
    “Yes
    -0.23
    POSITIVE LOGITS
     seeing
    0.56
     at
    0.46
    è§ģ
    0.43
    è¦ĭ
    0.40
    seeing
    0.40
     sees
    0.38
     see
    0.38
     entering
    0.37
     noticing
    0.36
     witnessing
    0.36
    Activations Density 0.887%

    No Known Activations