© 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. 42688
    Prev
    Next
    INDEX
    Explanations

    Indian currency denominations

    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
    å½Ĵ
    -0.27
     Binder
    -0.27
    |^
    -0.26
    ç¼ĩ
    -0.26
    æĭ¨
    -0.24
    èijļ
    -0.24
    _nm
    -0.24
    imi
    -0.24
     vi
    -0.23
     norms
    -0.23
    POSITIVE LOGITS
     lac
    0.59
     Lac
    0.56
     cro
    0.53
    lac
    0.51
     Lak
    0.45
    cro
    0.45
     Cro
    0.44
    lap
    0.43
     lak
    0.42
    Cro
    0.40
    Activations Density 0.009%

    No Known Activations