© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38251
    Prev
    Next
    INDEX
    Explanations

    authors of texts

    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
    裸
    -0.09
    ç½®æį¢
    -0.08
    indle
    -0.08
     апÑĢ
    -0.08
    amel
    -0.08
    åįĬå¹´
    -0.08
    è®®æ¡Ī
    -0.08
    bish
    -0.08
     гол
    -0.08
     Distrib
    -0.08
    POSITIVE LOGITS
    æĺİ代
    0.10
    çĶ°åĽŃ
    0.10
    çĻ¾å®¶
    0.10
    è¯ĭ
    0.10
    æĺ¯æĪijåĽ½
    0.09
    å¤įåı¤
    0.09
    ç¬Ķè®°
    0.09
    krit
    0.09
    _rewards
    0.09
    æĺİæľĿ
    0.09
    Activations Density 0.235%

    No Known Activations