© 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. 1734
    Prev
    Next
    INDEX
    Explanations

    line break

    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
    ä¸Ģæŀļ
    -0.09
    ä¸ĩåĪĨ
    -0.09
    毫
    -0.09
    üstü
    -0.09
    çī©
    -0.09
    驾
    -0.09
    /repos
    -0.09
    affer
    -0.08
    ErrorHandler
    -0.08
    æĮĩå¼ķ
    -0.08
    POSITIVE LOGITS
     break
    0.11
    lines
    0.10
    line
    0.10
    break
    0.10
    _break
    0.10
    åĪĨè¡Į
    0.10
    .break
    0.09
    -line
    0.09
    Break
    0.09
     lines
    0.09
    Activations Density 0.187%

    No Known Activations