© 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. 50497
    Prev
    Next
    INDEX
    Explanations

    victory or win

    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
    注æĺİåĩºå¤Ħ
    -0.10
    åĩºåħ¥
    -0.09
    积èĵĦ
    -0.08
    éķ¿çŁŃ
    -0.08
    èĨĺ
    -0.08
     Jenner
    -0.08
    ParameterValue
    -0.08
    è¯Ħ为
    -0.08
    éĤ£æ®µ
    -0.08
    çĤ³
    -0.08
    POSITIVE LOGITS
     ê²°êµŃ
    0.10
    æĸij
    0.09
    ewis
    0.09
    оÑģоб
    0.08
    곡
    0.08
    ç¬ij
    0.08
    icho
    0.08
    /goto
    0.08
    ieving
    0.08
    ìľ
    0.08
    Activations Density 0.028%

    No Known Activations