© 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. 32041
    Prev
    Next
    INDEX
    Explanations

    water damage, rescue, resistance

    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
    çīĻ
    -0.08
    幡
    -0.08
    ApiClient
    -0.08
    _snapshot
    -0.08
     chÄĥm
    -0.08
     Äijá»ķ
    -0.08
     reck
    -0.08
    RAL
    -0.08
     conc
    -0.08
    èģĶ
    -0.07
    POSITIVE LOGITS
    åĩłå¼ł
    0.12
    åĿ»
    0.10
    å¿ĥçģµ
    0.10
    ç«ĭåĪ»
    0.10
    æ¿¡
    0.10
    ạc
    0.10
    ç²ĺ
    0.10
    è£ħå¤ĩåĪ¶éĢł
    0.09
    æįŀ
    0.09
    沤
    0.09
    Activations Density 0.084%

    No Known Activations