© 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. 31205
    Prev
    Next
    INDEX
    Explanations

    intake or load followed by unrelated word

    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
    éĩijéĵ¶
    -0.10
    åħįç¨İ
    -0.10
    ç¬Ķè®°æľ¬
    -0.10
    ä¸İæѤ
    -0.10
    举æŃ¢
    -0.09
    åĴ¬
    -0.09
    çIJĽ
    -0.09
    .UUID
    -0.08
    éĶ¦ç»£
    -0.08
    åīįæĸ¹
    -0.08
    POSITIVE LOGITS
    èħĮ
    0.12
    åĴ¸
    0.09
    åѦèĢħ
    0.09
    滩
    0.09
    éĴł
    0.09
    Na
    0.09
    éĴĿ
    0.09
     salty
    0.09
     Na
    0.09
    æ²»çIJĨ
    0.09
    Activations Density 0.083%

    No Known Activations