© 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. 35840
    Prev
    Next
    INDEX
    Explanations

    sports training and safety

    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
    å¾ģ
    -0.09
    mort
    -0.09
     Lump
    -0.09
    è°Ł
    -0.08
    ieee
    -0.08
    ä¼°
    -0.08
     Schmidt
    -0.08
    治好
    -0.08
    常å§Ķä¼ļ
    -0.08
    å®īæħ°
    -0.08
    POSITIVE LOGITS
    essen
    0.10
    驾
    0.09
    _userdata
    0.09
    ä¿Ŀå®ī
    0.09
     Geb
    0.09
    EMON
    0.09
    inka
    0.09
    笼
    0.08
     lesion
    0.08
    âį
    0.08
    Activations Density 0.112%

    No Known Activations