© 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. 43016
    Prev
    Next
    INDEX
    Explanations

    ®

    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
    's
    -0.47
    ’s
    -0.40
    \n
    -0.37
    ↵ ↵
    -0.37
    'S
    -0.37
    \u
    -0.35
    ‘s
    -0.34
    ´s
    -0.34
    ↵  ↵
    -0.34
    "s
    -0.34
    POSITIVE LOGITS
     Blast
    0.28
    ãģ¦ãģĦãģı
    0.27
    edBy
    0.26
    ([]*
    0.25
    lä
    0.25
     Scale
    0.25
    press
    0.24
    CAPE
    0.24
    xfb
    0.24
    apid
    0.23
    Activations Density 0.006%

    No Known Activations