© 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. 49198
    Prev
    Next
    INDEX
    Explanations

    prospective study or trials

    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
    夺
    -0.09
    æijĺ
    -0.08
    æĦ¿æĦı
    -0.08
    ä½Ĩä¸įéĻIJäºİ
    -0.08
     vak
    -0.08
    åºŁæ°Ķ
    -0.08
    ivec
    -0.08
    TL
    -0.08
     anc
    -0.07
    ä¸Ģ线
    -0.07
    POSITIVE LOGITS
    å±ķæľĽ
    0.14
    åĽŀé¦ĸ
    0.11
    éģİåİ»
    0.11
    æ·±è¿ľ
    0.10
    渺
    0.10
    çľĭåIJij
    0.10
    _FORWARD
    0.10
    é¢ĦåijĬ
    0.10
    å¿Ĩ
    0.10
    è¿ĩåİ»
    0.10
    Activations Density 0.086%

    No Known Activations