© 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. 11738
    Prev
    Next
    INDEX
    Explanations

    countless

    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
    åįģ足
    -0.11
    é«»
    -0.10
    igel
    -0.09
    er
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.09
    ãģĭãģĦ
    -0.08
    å°ıå·§
    -0.08
    à¹īà¸Ńย
    -0.08
    å¾Ī强
    -0.07
    ArrayOf
    -0.07
    POSITIVE LOGITS
    ingly
    0.11
    enance
    0.11
    aneous
    0.10
    æĿĵ
    0.10
    aneously
    0.10
    çĪº
    0.09
    erno
    0.09
    0.09
    ernal
    0.09
    æĹłæķ°
    0.09
    Activations Density 0.003%

    No Known Activations