© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3936
    Prev
    Next
    INDEX
    Explanations

    scar tissue and deformities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĻļ
    -0.09
    èĪ
    -0.09
     Wh
    -0.08
    éŃĤ
    -0.08
    绿水
    -0.08
    èĮĨ
    -0.08
    -controls
    -0.08
    åħħ
    -0.08
     squeeze
    -0.08
     furn
    -0.08
    POSITIVE LOGITS
    çĸ¤çĹķ
    0.18
    çķ¸å½¢
    0.16
     scar
    0.14
     scars
    0.14
    çĸ¤
    0.14
    çķ¸
    0.14
    缺éĻ·
    0.13
    çijķçĸµ
    0.13
     Scar
    0.12
    çĹĤ
    0.12
    Activations Density 0.139%

    No Known Activations