© 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. 2918
    Prev
    Next
    INDEX
    Explanations

    methoxy-ox-

    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
    æ·±åĮĸæĶ¹éĿ©
    -0.10
    èĢģ头
    -0.09
    oger
    -0.08
    ẳ
    -0.08
    lös
    -0.08
    remen
    -0.08
    sWith
    -0.08
    订è´Ń
    -0.08
    对çŃĸ
    -0.08
    çĶª
    -0.08
    POSITIVE LOGITS
    åĿĿ
    0.10
    å¤ĸæĿ¥
    0.09
    ault
    0.09
    наÑĤ
    0.09
    羣çļ®
    0.09
    å®ŀè´¨
    0.09
    èĭ¦
    0.09
    elts
    0.09
    樱èĬ±
    0.09
     Affero
    0.08
    Activations Density 0.004%

    No Known Activations