© 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. 58872
    Prev
    Next
    INDEX
    Explanations

    family members

    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
    çĪ¶åŃIJ
    -0.09
    ãģįãģŁ
    -0.09
    ä¸ĢæĿ¡é¾Ļ
    -0.08
    Wi
    -0.08
    å°Ķæĸ¯
    -0.08
    è¿Ļç¯ĩ
    -0.08
    EDIA
    -0.08
    young
    -0.08
     SIG
    -0.08
    phans
    -0.08
    POSITIVE LOGITS
    çķĽ
    0.12
    çŁ¾
    0.09
    æĬµè¾¾
    0.09
    idget
    0.09
    èªĬ
    0.09
    诨
    0.09
    æĸ°å½¢åĬ¿ä¸ĭ
    0.09
    æĽ¾ä»»
    0.08
    -picker
    0.08
    picker
    0.08
    Activations Density 0.008%

    No Known Activations