© 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. 23488
    Prev
    Next
    INDEX
    Explanations

    transformation or changing form

    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
    çīµ
    -0.10
    çĤ¹ç¼Ģ
    -0.09
    pped
    -0.09
     Sparse
    -0.09
    haus
    -0.09
    çĸı
    -0.09
    tro
    -0.08
    åĹľ
    -0.08
    çī½
    -0.08
    inia
    -0.08
    POSITIVE LOGITS
    å¤ĸå½¢
    0.15
    åıĺå½¢
    0.14
    shape
    0.13
     shape
    0.12
    åĮĸ身
    0.12
    å½¢æĢģ
    0.12
    å½¢çĬ¶
    0.12
    _shape
    0.11
    åĮĸ
    0.11
    å½¢å¼ı
    0.10
    Activations Density 0.194%

    No Known Activations