© 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. 63032
    Prev
    Next
    INDEX
    Explanations

    saw or see

    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
    lea
    -0.10
    è¾Ł
    -0.10
    	TokenName
    -0.10
    ä¸įä½ı
    -0.09
    á»ijn
    -0.09
    ç»Ī
    -0.09
    .Pointer
    -0.09
    声èªī
    -0.09
    åİļ
    -0.09
    IENT
    -0.09
    POSITIVE LOGITS
    æŃ£åľ¨è¿Ľè¡Į
    0.11
    è¦ĭãģŁ
    0.09
    æĥŃ
    0.08
    çݰ象
    0.08
    çľĭè§ģ
    0.08
    åĻĻ
    0.08
    æѦè£ħ
    0.08
    å°ijè§ģ
    0.08
    é¡·
    0.08
    没è§ģè¿ĩ
    0.08
    Activations Density 0.043%

    No Known Activations