© 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. 43556
    Prev
    Next
    INDEX
    Explanations

    Beginning of documents

    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
    ester
    -0.32
    inals
    -0.29
    hen
    -0.29
    Hang
    -0.27
    het
    -0.27
    çĥ¯
    -0.26
     pal
    -0.26
    uala
    -0.26
     Hen
    -0.25
    hang
    -0.25
    POSITIVE LOGITS
    sse
    0.30
    å¤įå·¥
    0.28
     GP
    0.26
    ä»·
    0.25
    aclass
    0.24
     electromagnetic
    0.23
    åĶ¯
    0.23
     privat
    0.23
    .attach
    0.23
    _ev
    0.23
    Activations Density 0.000%

    No Known Activations