© 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. 52842
    Prev
    Next
    INDEX
    Explanations

    post office

    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
    à¤ĺ
    -0.08
    _months
    -0.08
    CLA
    -0.08
    èĻı
    -0.08
    oku
    -0.08
     Lesser
    -0.08
    InProgress
    -0.08
    é½IJ
    -0.08
    PRS
    -0.08
    çĿ¬
    -0.08
    POSITIVE LOGITS
     yazılı
    0.09
    èĽ®
    0.09
    å¢ŀæĶ¶
    0.09
    æķ°æį®æĺ¾ç¤º
    0.09
    éļĪ
    0.09
     Hayward
    0.08
    еÑĩ
    0.08
    çĶ°åĽŃ
    0.08
    鬥
    0.08
    een
    0.08
    Activations Density 0.016%

    No Known Activations