© 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. 43595
    Prev
    Next
    INDEX
    Explanations

    scientific/technical writing

    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
    缮
    -0.30
    æ¨Ĭ
    -0.25
    è°·
    -0.25
    rg
    -0.25
    ãĤĭ
    -0.25
    erox
    -0.25
    è§Ĵ
    -0.25
     hoped
    -0.25
    çĴ°
    -0.24
    ×ķ×Ļ
    -0.24
    POSITIVE LOGITS
    å°¼äºļ
    0.30
    icans
    0.27
     nämlich
    0.26
    è³ĵ
    0.25
     Tops
    0.25
     Sabb
    0.25
    пла
    0.25
    å¼ĢéŨ
    0.24
    /javascript
    0.24
    abo
    0.24
    Activations Density 0.002%

    No Known Activations