© 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. 31-TRANSCODER-HP
    7. 19083
    Prev
    Next
    INDEX
    Explanations

    well

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pop
    -0.40
    pop
    -0.39
     Pop
    -0.37
    Pop
    -0.37
     POP
    -0.32
    _POP
    -0.32
    _pop
    -0.29
    Om
    -0.29
    .pop
    -0.29
     obsc
    -0.28
    POSITIVE LOGITS
     well
    0.34
    well
    0.30
     known
    0.30
    -known
    0.29
    深深çļĦ
    0.27
    ICLE
    0.27
    ycin
    0.27
    yro
    0.27
    é¹ij
    0.27
     Well
    0.26
    Activations Density 0.014%

    No Known Activations