© 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. 11511
    Prev
    Next
    INDEX
    Explanations

    collection of

    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
    çĹĽ
    -0.10
    åıijæĺİ
    -0.10
    ÐĴидео
    -0.08
    è·¯æ¼Ķ
    -0.08
    ÉĻ
    -0.08
    ardin
    -0.08
     Ùĥب
    -0.08
    ç¢į
    -0.08
     csvfile
    -0.08
    jem
    -0.08
    POSITIVE LOGITS
    æ±ĩ
    0.13
    éĽĨç»ĵ
    0.11
    æ±ĩéĽĨ
    0.11
    è¾ij
    0.10
    éĽĨ
    0.10
    ç²¾éĢī
    0.10
     collection
    0.10
     collections
    0.09
    å¿IJ
    0.09
    éĽĨåIJĪ
    0.09
    Activations Density 0.070%

    No Known Activations