© 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. 43072
    Prev
    Next
    INDEX
    Explanations

    frying and grilling

    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
    åŀĴ
    -0.27
    èIJ¥
    -0.27
    å¼Ħ
    -0.25
    nect
    -0.24
    å¿Ĺ
    -0.24
     Че
    -0.23
    åļ¼
    -0.23
    BW
    -0.23
    çĩĥ
    -0.23
    çĵł
    -0.23
    POSITIVE LOGITS
    é¦ĸ次
    0.30
    kas
    0.28
    иÑĢ
    0.27
     bron
    0.27
    erde
    0.27
    ir
    0.26
    utters
    0.26
     bread
    0.26
    -f
    0.25
    ÑĤÑĮÑģÑı
    0.25
    Activations Density 0.002%

    No Known Activations