© 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. 32-TRANSCODER-HP
    7. 41336
    Prev
    Next
    INDEX
    Explanations

    Alexander

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PRS
    -0.27
    交
    -0.27
    ito
    -0.26
    bay
    -0.25
    æ¶Ī
    -0.24
    è·ĥ
    -0.24
    ertz
    -0.24
    appers
    -0.24
    DRAM
    -0.24
    itar
    -0.24
    POSITIVE LOGITS
    æį¢æĪIJ
    0.27
     incomes
    0.26
     hung
    0.26
    ocha
    0.26
    åľĺ
    0.26
    gm
    0.25
     rooting
    0.25
    æIJŀå¾Ĺ
    0.24
    TokenType
    0.24
     MILL
    0.24
    Activations Density 0.001%

    No Known Activations