© 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. 43298
    Prev
    Next
    INDEX
    Explanations

    to

    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
     khÃŃ
    -0.29
     very
    -0.28
     –
    -0.27
    theless
    -0.26
     with
    -0.26
    æ¡Ĩ
    -0.26
    ä¹Łå¾Ī
    -0.26
     --
    -0.25
    ids
    -0.25
    æĥŁ
    -0.25
    POSITIVE LOGITS
    ertz
    0.32
    played
    0.32
    ITU
    0.29
     don
    0.29
    ainless
    0.28
    ioned
    0.28
    LLU
    0.28
    abled
    0.27
    bé
    0.27
    icious
    0.26
    Activations Density 0.006%

    No Known Activations