© 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. 10121
    Prev
    Next
    INDEX
    Explanations

    asking for help or needing something

    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
    解æĶ¾æĢĿæĥ³
    -0.10
    ustin
    -0.09
    æĸ¼æĺ¯
    -0.09
    ifiers
    -0.09
    .stub
    -0.08
    åĩłå¼ł
    -0.08
    ainty
    -0.08
    abbo
    -0.08
    scopes
    -0.08
    æīĭä¸Ń
    -0.08
    POSITIVE LOGITS
    idden
    0.10
    needed
    0.10
     needed
    0.09
    大家ä¸Ģèµ·
    0.09
    æ¶İ
    0.09
     اÙĦÙĦازÙħØ©
    0.09
    çĪ¿
    0.09
     necessary
    0.09
    iliation
    0.08
     Dom
    0.08
    Activations Density 0.146%

    No Known Activations