© 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. 53120
    Prev
    Next
    INDEX
    Explanations

    names and suffixes

    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
    æĵº
    -0.10
     Fritz
    -0.10
    书记
    -0.10
    ANGO
    -0.10
    åIJĦè¡Į
    -0.09
     sidl
    -0.09
    PMC
    -0.09
    -gnu
    -0.09
    LEC
    -0.09
    ä¸įåĪĨ
    -0.09
    POSITIVE LOGITS
    .tem
    0.09
     nec
    0.09
    æĺ§
    0.08
     accomp
    0.08
    ä¼Łå¤§
    0.08
    æ¯ĭ
    0.08
    èijĹ
    0.08
    bens
    0.08
    èij«èĬ¦
    0.08
    åĶ¤éĨĴ
    0.08
    Activations Density 0.033%

    No Known Activations