© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8522
    Prev
    Next
    INDEX
    Explanations

    taking actions or items

    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
    带åΰ
    -0.09
     Mile
    -0.09
    ewolf
    -0.08
    ossal
    -0.08
    /lic
    -0.08
    è±¢
    -0.08
    ä¼ļå½±åĵįåΰ
    -0.08
     spread
    -0.08
    á»ĩ
    -0.08
    agas
    -0.08
    POSITIVE LOGITS
    ook
    0.10
    çŀ©çĽ®
    0.09
    转载请
    0.08
    éĢĽè¡Ĺ
    0.08
    èİ«è¿ĩäºİ
    0.08
    _CLI
    0.08
    é¾Į
    0.08
    .orig
    0.08
    abil
    0.08
    AndServe
    0.08
    Activations Density 0.059%

    No Known Activations