© 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. 49252
    Prev
    Next
    INDEX
    Explanations

    calling party or caller ID

    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
    çĶµè¯Ŀ
    -0.11
    æīĵçĶµè¯Ŀ
    -0.11
    éĽ»è©±
    -0.10
    èĽĢ
    -0.10
    ç»ı纪人
    -0.10
     disp
    -0.09
    çŁŃä¿¡
    -0.09
    鼳
    -0.09
    泪
    -0.09
    _email
    -0.09
    POSITIVE LOGITS
    å°Ĭ
    0.09
    æıIJåĩºçļĦ
    0.08
    å°Ĭæķ¬
    0.08
    çĤ³
    0.08
    æīĢ说çļĦ
    0.08
    tips
    0.08
    æ§IJ
    0.08
    ç¼Ń
    0.08
    说æĪij
    0.08
    æĬĬèĩªå·±çļĦ
    0.08
    Activations Density 0.040%

    No Known Activations