© 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. 53143
    Prev
    Next
    INDEX
    Explanations

    available under or at

    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
    alth
    -0.10
    èģĬ
    -0.09
    è°¤
    -0.09
    çģ¾å®³
    -0.09
    å¯Į豪
    -0.09
    éªĮè¯ģçłģ
    -0.09
    eka
    -0.08
    htt
    -0.08
    åīĶ
    -0.08
    èµĿ
    -0.08
    POSITIVE LOGITS
    å¼Ħ
    0.12
    haus
    0.10
    çıł
    0.09
    ensem
    0.09
    æIJŀ
    0.09
    otos
    0.09
    quent
    0.09
    гал
    0.09
     Curso
    0.09
    æľ
    0.09
    Activations Density 0.061%

    No Known Activations