© 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. 42674
    Prev
    Next
    INDEX
    Explanations

    Technical research/information

    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
    arrings
    -0.30
    INET
    -0.26
    ért
    -0.25
    ingt
    -0.25
    ingroup
    -0.25
    INTR
    -0.25
    elite
    -0.25
    uling
    -0.24
    idget
    -0.24
    _OT
    -0.24
    POSITIVE LOGITS
    说èĩªå·±
    0.28
    ENTION
    0.28
    纳
    0.28
    AppBar
    0.26
    æľ¬æĬ¥
    0.26
    cept
    0.26
    ^n
    0.25
     vi
    0.25
     syn
    0.25
    ç´į
    0.24
    Activations Density 0.010%

    No Known Activations