© 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. 11108
    Prev
    Next
    INDEX
    Explanations

    photo shoot

    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
    oter
    -0.09
    缣
    -0.09
    åıijå±ķä¸Ń
    -0.08
    در
    -0.08
    åģļèµ·
    -0.08
    人éĹ´
    -0.08
    åĩºåı£
    -0.08
    èĢģæŧ
    -0.08
     Anonymous
    -0.08
    chap
    -0.08
    POSITIVE LOGITS
    edImage
    0.09
    ä»İæł¹æľ¬ä¸Ĭ
    0.09
    ÙĪÙĬر
    0.09
    æľ¬ç«Ļ
    0.09
    大声
    0.09
    lesi
    0.09
    å¤Ħæĸ¹
    0.08
     Besch
    0.08
     Nets
    0.08
    æŀ¶
    0.08
    Activations Density 0.014%

    No Known Activations