© 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. 22828
    Prev
    Next
    INDEX
    Explanations

    programming

    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
    Spacing
    -0.29
    Ïī
    -0.26
    ÏĦ
    -0.25
     пÑĢож
    -0.25
     Called
    -0.25
    ship
    -0.25
     Shore
    -0.24
    å¿«
    -0.24
    å½¼
    -0.24
    lik
    -0.24
    POSITIVE LOGITS
    otland
    0.29
    agos
    0.28
     subrange
    0.28
    imagem
    0.28
    expo
    0.27
     gob
    0.26
     DropIndex
    0.26
    lep
    0.26
    æµ·éĩı
    0.26
    åľ¨å®¶éĩĮ
    0.26
    Activations Density 0.004%

    No Known Activations