© 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. 38725
    Prev
    Next
    INDEX
    Explanations

    free consultation

    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
    ç£ķ
    -0.09
    ªĮ
    -0.08
    yp
    -0.08
    åīĶ
    -0.08
    ä»ij
    -0.08
     Pascal
    -0.08
    ams
    -0.08
    修补
    -0.08
    ucci
    -0.08
    æŶæŶ
    -0.08
    POSITIVE LOGITS
    inia
    0.12
    åĮ¹
    0.11
    å°±è¿ij
    0.11
    ðŁĵŀ
    0.11
    éĽ»è©±
    0.11
    à¹Ĥà¸Ĺร
    0.10
    åĪĿæŃ¥
    0.10
    æݥ触
    0.10
    éĶĢåĶ®äººåijĺ
    0.10
     Fax
    0.09
    Activations Density 0.075%

    No Known Activations