© 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. 43145
    Prev
    Next
    INDEX
    Explanations

    Conversational or incomplete text

    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
     carefully
    -0.28
    rase
    -0.27
    å®Įåħ¨åı¯ä»¥
    -0.25
    åŃļ
    -0.25
    eme
    -0.24
    (compact
    -0.24
    失
    -0.24
    utors
    -0.24
    eshire
    -0.24
     exhausting
    -0.24
    POSITIVE LOGITS
    -w
    0.52
     ell
    0.43
    ell
    0.43
    ellan
    0.40
    wo
    0.38
    ãĤ¦ãĤ§
    0.37
    _w
    0.36
    ELL
    0.36
    ellen
    0.35
    Very
    0.35
    Activations Density 0.004%

    No Known Activations