© 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. 57942
    Prev
    Next
    INDEX
    Explanations

    bourbon barrel and Almond defeated

    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
    lement
    -0.11
    uter
    -0.11
    bourne
    -0.10
    lements
    -0.10
     ÐľÐ¾Ñģк
    -0.09
     chóng
    -0.09
    ç¹ģèį£
    -0.09
    éĢłæŀĹ
    -0.09
    éĥ½éĿŀ常
    -0.09
    bies
    -0.09
    POSITIVE LOGITS
    beck
    0.10
    atis
    0.09
    å¤Ń
    0.09
    wich
    0.08
    大使
    0.08
    acles
    0.08
    icum
    0.08
    _HC
    0.07
    onis
    0.07
    alto
    0.07
    Activations Density 0.013%

    No Known Activations