© 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. 32731
    Prev
    Next
    INDEX
    Explanations

    double checked

    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
    éĶī
    -0.11
    ibri
    -0.10
    ä½łåĸľæ¬¢
    -0.10
    æļ´
    -0.09
    çĽİ
    -0.09
    .Interop
    -0.09
    ä¸Ģä¼ļåĦ¿
    -0.09
    åĪĽéĢłæĢ§
    -0.09
    amac
    -0.09
    åĨ¥
    -0.09
    POSITIVE LOGITS
    ä¸Ģç¬ij
    0.11
    ınd
    0.10
    亲
    0.10
     взглÑıд
    0.09
    çľĭäºĨä¸Ģçľ¼
    0.09
    åĩºéŨ
    0.08
     dances
    0.08
    é¼»
    0.08
    ha
    0.08
    zy
    0.08
    Activations Density 0.062%

    No Known Activations