© 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. 53923
    Prev
    Next
    INDEX
    Explanations

    quotation marks followed by common words

    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
    suming
    -0.10
    inton
    -0.09
    hower
    -0.09
    æīĢ产çĶŁçļĦ
    -0.09
    å§ĭç»ĪåĿļæĮģ
    -0.09
    èĤĸ
    -0.09
    ingly
    -0.09
    _INTERRUPT
    -0.09
    STEM
    -0.09
     Spears
    -0.09
    POSITIVE LOGITS
    åı¦
    0.09
    å¤ĸéĿ¢
    0.08
    åı¦ä¸ĢåįĬ
    0.08
    æ¯Ķè¾ĥ好
    0.08
    ful
    0.08
    ifs
    0.07
    管çIJĨåĴĮ
    0.07
    仨
    0.07
    帽
    0.07
     fi
    0.07
    Activations Density 0.233%

    No Known Activations