© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 23382
    Prev
    Next
    INDEX
    Explanations

    Uncertainty or conditionality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    pecies
    -0.28
    aptic
    -0.25
    紧紧
    -0.24
    IDS
    -0.23
    ODE
    -0.23
    exus
    -0.23
    áo
    -0.23
    åķ¸
    -0.23
    _NR
    -0.23
    WSC
    -0.23
    POSITIVE LOGITS
     otherwise
    1.84
    otherwise
    1.57
    åIJ¦åĪĻ
    1.52
     Otherwise
    1.46
    Otherwise
    1.34
    ä¸įçĦ¶
    1.34
    åIJ¦åīĩ
    1.20
     OTHERWISE
    1.18
     else
    0.97
    else
    0.92
    Activations Density 0.031%

    No Known Activations