© 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. 7495
    Prev
    Next
    INDEX
    Explanations

    weight and body weight

    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
    erable
    -0.10
    å®ģ
    -0.10
    平淡
    -0.09
    é«ĺä½į
    -0.08
    adians
    -0.08
    寧
    -0.08
    ç¥ŀå¥ĩ
    -0.08
     Knock
    -0.08
    çļĦéĢŁåº¦
    -0.08
    ãĤŃãĥ¥
    -0.08
    POSITIVE LOGITS
    ä½ĵéĩį
    0.21
     weight
    0.20
    éĩįéĩı
    0.18
     Weight
    0.16
    weigh
    0.15
    weight
    0.15
     weighing
    0.15
    .Weight
    0.15
     weigh
    0.15
    .weight
    0.14
    Activations Density 0.085%

    No Known Activations