© 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. 48181
    Prev
    Next
    INDEX
    Explanations

    lot of

    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
    åĵĪå°Ķ
    -0.10
     COPYRIGHT
    -0.09
    åĴ¬
    -0.09
    erver
    -0.08
    essen
    -0.08
    æѤ
    -0.08
    restore
    -0.08
    æµĵæµĵ
    -0.08
    å¾Ī强
    -0.08
    illed
    -0.08
    POSITIVE LOGITS
    UNCH
    0.09
    è¥
    0.09
     ÑĥÑĩаÑģÑĤ
    0.08
    çĪº
    0.08
     Aynı
    0.08
    anna
    0.08
    ãģĬãģı
    0.08
    èĩ
    0.08
    org
    0.08
    indi
    0.08
    Activations Density 0.014%

    No Known Activations