© 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. 38836
    Prev
    Next
    INDEX
    Explanations

    phone numbers and addresses

    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
    失èIJ½
    -0.10
    yer
    -0.10
    ç°¸
    -0.10
    uary
    -0.09
    eya
    -0.09
    ä»ij
    -0.09
    åģ¶çĦ¶
    -0.09
    äºĭåIJİ
    -0.09
    æ¿ĢçĥĪ
    -0.09
    涸
    -0.09
    POSITIVE LOGITS
    庵
    0.09
    ä¸ĸ家
    0.09
    retty
    0.08
    èģĶç³»
    0.08
    èįŁ
    0.08
    tré
    0.08
    串
    0.07
     Hor
    0.07
    æ§IJ
    0.07
    .registry
    0.07
    Activations Density 0.081%

    No Known Activations