© 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. 1476
    Prev
    Next
    INDEX
    Explanations

    pattern of

    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
    itution
    -0.10
    çīĿ
    -0.09
    ðŁı»
    -0.09
    yard
    -0.09
    裳
    -0.09
    å®ļå¾ĭ
    -0.09
    byn
    -0.09
    quir
    -0.09
    裹
    -0.09
    ilia
    -0.09
    POSITIVE LOGITS
     Pattern
    0.11
    atics
    0.10
    -pattern
    0.10
    .Pattern
    0.10
    (pattern
    0.10
     pattern
    0.10
    setter
    0.09
    .pattern
    0.09
    ities
    0.09
     patterns
    0.09
    Activations Density 0.056%

    No Known Activations