© 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. 42122
    Prev
    Next
    INDEX
    Explanations

    skin conditions and damage

    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
    马æĭī
    -0.27
    ingroup
    -0.26
    è¯ģæĺİ
    -0.26
     proof
    -0.26
     remote
    -0.25
     banda
    -0.25
    permanent
    -0.25
    æŃ¥
    -0.24
    æİī
    -0.24
    å
    -0.24
    POSITIVE LOGITS
    篦
    0.29
    æ£ķ
    0.27
    spots
    0.27
    è´£ç¼ĸ
    0.27
    low
    0.27
    light
    0.27
    èŀºæĹĭ
    0.26
     gan
    0.25
    Light
    0.25
     Pell
    0.25
    Activations Density 0.001%

    No Known Activations