© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29584
    Prev
    Next
    INDEX
    Explanations

    keys

    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
    Negative Logits
    å¹ķ
    -0.10
    æļ®
    -0.09
    åĢ¡
    -0.09
    è§ĩ
    -0.09
    æģĤ
    -0.09
    çŧ
    -0.09
    è´¡çĮ®
    -0.09
    忱
    -0.08
    ItemSelected
    -0.08
    å¼Ħ
    -0.08
    POSITIVE LOGITS
    éĴ¥åĮĻ
    0.25
     keys
    0.18
    éĴ¥
    0.17
    keys
    0.15
     Keys
    0.13
    Keys
    0.13
    (keys
    0.12
    _KEYS
    0.11
    _keys
    0.11
    ðŁĶij
    0.11
    Activations Density 0.062%

    No Known Activations