© 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. 53257
    Prev
    Next
    INDEX
    Explanations

    hybrid vehicle

    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
    uset
    -0.10
    esting
    -0.09
    ä¸įè¦ģåĨį
    -0.08
    reat
    -0.08
    sel
    -0.08
    åIJİæŀľ
    -0.08
    æ¥ŀ
    -0.08
    éļħ
    -0.08
    èĢĺ
    -0.08
    è¹Ī
    -0.08
    POSITIVE LOGITS
    ity
    0.10
    ization
    0.10
    ï¸
    0.10
    æ²ĵ
    0.10
    town
    0.10
    icum
    0.09
    ized
    0.09
    alar
    0.09
    usercontent
    0.09
    ität
    0.09
    Activations Density 0.021%

    No Known Activations