© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35785
    Prev
    Next
    INDEX
    Explanations

    Schneider surname

    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
    0
    -0.10
    3
    -0.09
    8
    -0.09
    ertz
    -0.09
    ecs
    -0.09
    级以ä¸Ĭ
    -0.09
    1
    -0.09
    5
    -0.09
    ä¸ļä½Ļ
    -0.09
    æ®Ĩ
    -0.09
    POSITIVE LOGITS
     Kimber
    0.09
    èĩªæѤ
    0.09
    combe
    0.09
    жив
    0.09
    er
    0.08
    aptor
    0.08
    OWER
    0.08
    æ¢Ĩ
    0.08
    ling
    0.08
    aul
    0.08
    Activations Density 0.003%

    No Known Activations