© 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. 10773
    Prev
    Next
    INDEX
    Explanations

    dynamic and its follow-ons

    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
    ings
    -0.10
    ä¼Ĺ
    -0.10
    ricular
    -0.09
    зна
    -0.09
    Ìģ
    -0.09
    borg
    -0.08
     Rape
    -0.08
    à¤ŀ
    -0.08
    monic
    -0.08
    “He
    -0.08
    POSITIVE LOGITS
    强åĬĽ
    0.10
    èĪ¬çļĦ
    0.10
    iated
    0.10
    isContained
    0.09
    ä¸įæŃ»
    0.09
    èħ´
    0.09
    éĥ¨ä½į
    0.09
    eer
    0.09
     Wich
    0.09
    ä¸įå®ī
    0.09
    Activations Density 0.014%

    No Known Activations