© 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. 56307
    Prev
    Next
    INDEX
    Explanations

    essentials or items to use

    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
    rone
    -0.10
     circumstance
    -0.09
    åIJĦåľ°
    -0.09
    hana
    -0.09
    åľ¨æİ¥åıĹ
    -0.09
    èī°éļ¾
    -0.08
     candid
    -0.08
    åķ®
    -0.08
     Receipt
    -0.08
    槽
    -0.08
    POSITIVE LOGITS
    è£ħå¤ĩ
    0.11
    æŁĶ
    0.10
    Fcn
    0.10
    лом
    0.10
    æŁĶæĢ§
    0.10
    å¤ĩ
    0.10
    为ä¼ģä¸ļ
    0.09
    getCell
    0.09
    Cfg
    0.08
    pps
    0.08
    Activations Density 0.021%

    No Known Activations