© 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. 2909
    Prev
    Next
    INDEX
    Explanations

    will be

    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
     Wich
    -0.10
    æ´»
    -0.10
    æĭ¨
    -0.10
    eya
    -0.09
    URITY
    -0.09
    PAD
    -0.09
    prt
    -0.09
    èĢĮä¸Ķè¿ĺ
    -0.09
    legs
    -0.09
    .registry
    -0.09
    POSITIVE LOGITS
    äºĮåŃĹ
    0.09
    ä½ļ
    0.08
    乡
    0.08
    该æĿij
    0.08
    çĻ¸
    0.08
    çĿ£åĬŀ
    0.08
    èĵij
    0.08
     bidding
    0.08
    (util
    0.07
    âĶ
    0.07
    Activations Density 0.058%

    No Known Activations