© 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. 51314
    Prev
    Next
    INDEX
    Explanations

    iff followed by Lampe

    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
    çijķ
    -0.10
    iore
    -0.09
    _WR
    -0.09
     дело
    -0.09
     Coy
    -0.08
    èĵĭ
    -0.08
    è²ł
    -0.08
     Alabama
    -0.08
    ä½ľä¸ºä¸Ģç§į
    -0.08
    çݳ
    -0.08
    POSITIVE LOGITS
    å·¡åĽŀ
    0.11
    à¤Ĭ
    0.09
    æĹłéļľç¢į
    0.09
    æĬ¤åį«
    0.09
    绢
    0.09
    æłĩå¿ĹæĢ§
    0.09
    ç·Ĭ
    0.08
    izard
    0.08
    æĵĺ
    0.08
    иÑĤелÑĮн
    0.08
    Activations Density 0.036%

    No Known Activations