© 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. 35304
    Prev
    Next
    INDEX
    Explanations

    .com links and paths

    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
     보기
    -0.10
    èĭĵ
    -0.10
    æĪĺäºī
    -0.10
    éļ¶å±ŀ
    -0.09
    allis
    -0.09
    ÑĪе
    -0.09
    _sibling
    -0.09
    æĦ§
    -0.09
    涵
    -0.09
    导读
    -0.09
    POSITIVE LOGITS
    åĬĪ
    0.09
    CSI
    0.08
     Jag
    0.08
    éĶ¯
    0.08
    èĦĨ
    0.08
    é¡ĺ
    0.08
    htdocs
    0.08
    ÙĦاØŃ
    0.07
    hook
    0.07
    sheets
    0.07
    Activations Density 0.011%

    No Known Activations