© 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. 7127
    Prev
    Next
    INDEX
    Explanations

    connection with or related to

    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
    è¦ģåģļåĪ°
    -0.10
    ób
    -0.10
    onth
    -0.10
    æĸ°éĹ»ç½ij
    -0.09
     иÑģпол
    -0.09
     Celt
    -0.09
    ä¸ĵ家åѦèĢħ
    -0.09
    thon
    -0.09
    ãģ©
    -0.09
    ä¸ĵ访
    -0.08
    POSITIVE LOGITS
    1
    0.09
    ä¹±
    0.08
    æ½ľ
    0.08
    åı²è¯Ĺ
    0.08
    0
    0.08
     custody
    0.08
    6
    0.08
    è¿«
    0.07
    2
    0.07
    轶
    0.07
    Activations Density 0.018%

    No Known Activations