© 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. 49633
    Prev
    Next
    INDEX
    Explanations

    well operations

    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
    æ±Łä¸ľ
    -0.09
    _ATOMIC
    -0.09
    ogan
    -0.09
     wedge
    -0.09
    _Db
    -0.09
    对åŃ©åŃIJ
    -0.09
    åİļ
    -0.08
    etz
    -0.08
    vara
    -0.08
    _retry
    -0.08
    POSITIVE LOGITS
    éĹ³
    0.10
     barrels
    0.09
    æ®Ĭ
    0.08
    spring
    0.08
    äºķ
    0.08
     uç
    0.08
    æĸ°æĬĢæľ¯
    0.08
    渫
    0.08
    书éĻ¢
    0.08
    ç»Ī端
    0.08
    Activations Density 0.058%

    No Known Activations