© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52067
    Prev
    Next
    INDEX
    Explanations

    what or how

    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
    æĶ¶å½ķ
    -0.09
    ลำ
    -0.09
    éĢIJ
    -0.08
    èį¦
    -0.08
    ents
    -0.08
    eten
    -0.08
     nowrap
    -0.08
     Studios
    -0.08
    éģĴ
    -0.08
    inline
    -0.08
    POSITIVE LOGITS
     Malays
    0.09
    åĪ©äºļ
    0.09
    çļĦéĴ±
    0.09
     JACK
    0.08
    åIJĦæľī
    0.08
    airie
    0.08
    igators
    0.08
    åIJįçīĮ
    0.08
    endi
    0.08
    .addObject
    0.08
    Activations Density 0.023%

    No Known Activations