© 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. 52524
    Prev
    Next
    INDEX
    Explanations

    free or not free

    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
    ä¸įæĺİ
    -0.09
    浩
    -0.08
     Panic
    -0.08
    åĩıåħį
    -0.08
    ãģĮãģ§ãģį
    -0.08
    è¿Ļ个éĹ®é¢ĺ
    -0.08
    oji
    -0.07
    .itemView
    -0.07
    artifact
    -0.07
    ä½ĺ
    -0.07
    POSITIVE LOGITS
    aryl
    0.09
    _ACTIV
    0.09
    istent
    0.09
    wers
    0.09
    éĵ¨
    0.09
     citiz
    0.08
    ä¹ĭ声
    0.08
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.08
    èĻij
    0.08
     mist
    0.08
    Activations Density 0.060%

    No Known Activations