© 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. 51292
    Prev
    Next
    INDEX
    Explanations

    describing states or facts

    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
    èĻ½
    -0.11
     zwar
    -0.09
    èĻ½çĦ¶
    -0.09
    éĽĸ
    -0.09
    ä½Ĩåľ¨
    -0.09
    .truth
    -0.09
     Chatt
    -0.08
     ТолÑĮко
    -0.08
    rlen
    -0.08
    åĢĴ
    -0.08
    POSITIVE LOGITS
    大èĩ´
    0.12
    èĤ¯å®ļæĺ¯
    0.10
    大æ¦Ĥ
    0.09
    大æ¦Ĥæĺ¯
    0.09
    èĬ¹
    0.09
    åıĹ
    0.09
    å¤ļåįĬ
    0.09
     somewhere
    0.09
    éĽķ
    0.08
    anz
    0.08
    Activations Density 0.096%

    No Known Activations