© 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. 42458
    Prev
    Next
    INDEX
    Explanations

    code/compiling

    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
    SION
    -0.28
    ylon
    -0.27
    ise
    -0.26
     ses
    -0.25
    olve
    -0.25
    åĨ¶
    -0.24
    »¿
    -0.24
    ä½Ł
    -0.24
    its
    -0.24
    uild
    -0.24
    POSITIVE LOGITS
    ar
    0.78
    AR
    0.64
    arin
    0.61
    ara
    0.60
    аÑĢ
    0.59
    aret
    0.56
    are
    0.56
    arem
    0.54
     ar
    0.54
    ari
    0.52
    Activations Density 0.012%

    No Known Activations