© 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. 61150
    Prev
    Next
    INDEX
    Explanations

    string and related sequences

    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
    å§Ĭ妹
    -0.08
     fist
    -0.08
    croft
    -0.08
    xing
    -0.08
    ä¹łæĥ¯
    -0.08
    妯
    -0.08
    åīįçŀ»
    -0.07
    绣é¢Ĩ
    -0.07
    /md
    -0.07
    éģĵ
    -0.07
    POSITIVE LOGITS
    sWith
    0.09
    ukes
    0.09
    çİij
    0.09
    еÑĢж
    0.09
    ified
    0.09
    åĬłå¿«å»ºè®¾
    0.09
     Phar
    0.09
     ëĶ°
    0.09
     Bund
    0.08
    spiel
    0.08
    Activations Density 0.040%

    No Known Activations