© 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. 33705
    Prev
    Next
    INDEX
    Explanations

    past experience or states

    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¯ı个人
    -0.09
    éĤĵå°ıå¹³
    -0.08
    çļĵ
    -0.08
    1
    -0.08
    oped
    -0.08
     blo
    -0.08
     Gael
    -0.08
    8
    -0.08
     Kirk
    -0.08
    åĨ¶
    -0.07
    POSITIVE LOGITS
    段æŶéĹ´
    0.10
    ç»ıéĶĢ
    0.10
    åIJĥè¿ĩ
    0.10
    ayah
    0.09
    以å¾Ģ
    0.09
    åİĨåı²
    0.08
     yapılan
    0.08
     recent
    0.08
    ç»ıåİĨè¿ĩ
    0.08
    æĽ¾
    0.08
    Activations Density 0.001%

    No Known Activations