© 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. 23690
    Prev
    Next
    INDEX
    Explanations

    read more

    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
    -0.10
    uro
    -0.10
    èĩªçIJĨ
    -0.09
    uros
    -0.09
    ëĭ¤ë©´
    -0.09
    宽æĿ¾
    -0.09
    PRETTY
    -0.09
    >*</
    -0.09
    elage
    -0.09
    强åĬ²
    -0.09
    POSITIVE LOGITS
    åĴ¨
    0.08
    neighbor
    0.08
    (/
    0.08
    ä»Ĭ天å°ıç¼ĸ
    0.08
    éļıåį³
    0.08
     Borg
    0.07
    jd
    0.07
    è·Ħ
    0.07
    éĤ»å±ħ
    0.07
     Bair
    0.07
    Activations Density 0.065%

    No Known Activations