© 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. 58375
    Prev
    Next
    INDEX
    Explanations

    continue to browse

    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
    å®ļäºĨ
    -0.12
    NSS
    -0.10
    teenth
    -0.09
    继ç»Ńä¿ĿæĮģ
    -0.09
    holes
    -0.09
    cel
    -0.09
    amp
    -0.09
    itect
    -0.09
    ä¸ĢåĪĻ
    -0.09
    ah
    -0.08
    POSITIVE LOGITS
    ance
    0.11
    ä¸įäºĨ
    0.11
    AINS
    0.10
    ence
    0.10
    SetValue
    0.10
    ances
    0.09
    éĻIJãĤĬ
    0.09
    ä¸įæĸŃçļĦ
    0.09
    ents
    0.09
    hin
    0.09
    Activations Density 0.041%

    No Known Activations