© 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. 26569
    Prev
    Next
    INDEX
    Explanations

    connect with

    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
    ogg
    -0.09
    骨æŀ¶
    -0.08
    icap
    -0.07
    宽带
    -0.07
    éĻĦåĬł
    -0.07
     Sche
    -0.07
     tap
    -0.07
     flick
    -0.07
    oses
    -0.07
     sap
    -0.07
    POSITIVE LOGITS
    è´»
    0.11
    äºĴéĢļ
    0.11
    æĩĭ
    0.10
    åıĭè°Ĭ
    0.10
    ç»ıæµİæĬĢæľ¯
    0.10
    æ¾į
    0.10
    æ»ĵ
    0.09
    失è°ĥ
    0.09
    åīįæīĢæľªæľī
    0.09
    è°Ĭ
    0.09
    Activations Density 0.011%

    No Known Activations