© 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. 31153
    Prev
    Next
    INDEX
    Explanations

    contents 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
     dur
    -0.09
    pis
    -0.09
    èIJ½ä¸ĭ
    -0.08
    assi
    -0.08
    ifer
    -0.08
    pone
    -0.08
    CDATA
    -0.08
    edList
    -0.08
    壮
    -0.08
    ä¸ľè¥¿
    -0.08
    POSITIVE LOGITS
     contents
    0.14
    Contents
    0.13
    _contents
    0.12
     Contents
    0.12
    æĪ·åı£
    0.12
    contents
    0.12
    .contents
    0.11
     CONTENT
    0.10
    (contents
    0.10
    åįļçī©
    0.09
    Activations Density 0.102%

    No Known Activations