© 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. 47932
    Prev
    Next
    INDEX
    Explanations

    always wanted

    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
    æ¡ħ
    -0.10
    èµ°å¾Ĺ
    -0.10
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.09
    allax
    -0.09
    обÑĭ
    -0.09
    顾èĻij
    -0.09
    失åĪ©
    -0.09
    éĻįä½İæĪIJæľ¬
    -0.09
    éĺĶ
    -0.09
    à§į
    -0.09
    POSITIVE LOGITS
    agas
    0.08
    amus
    0.08
    æ·¯
    0.08
     Gret
    0.08
    iates
    0.08
     propagation
    0.08
    为äºĨæĽ´å¥½
    0.08
    æľī个
    0.07
    ç¿»
    0.07
    ä¸Ģ件äºĭ
    0.07
    Activations Density 0.050%

    No Known Activations