© 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. 30563
    Prev
    Next
    INDEX
    Explanations

    do the same thing

    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
    å¦Ĭ
    -0.11
    æĵį
    -0.10
    夥
    -0.09
    åĵģç§į
    -0.09
    糧
    -0.09
    롤
    -0.09
    embro
    -0.09
    ç»ķ
    -0.09
    èĤ¯
    -0.09
    _DRV
    -0.09
    POSITIVE LOGITS
    å¯ĵ
    0.09
    缸å½ĵäºİ
    0.09
    äºĮèĢħ
    0.08
     bracket
    0.08
    aria
    0.08
    åĩŃè¯ģ
    0.08
    keys
    0.08
    æĭĶ
    0.08
    arily
    0.08
    ble
    0.08
    Activations Density 0.040%

    No Known Activations