© 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. 11902
    Prev
    Next
    INDEX
    Explanations

    (which had

    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
    stead
    -0.12
    OMEM
    -0.11
    iny
    -0.10
    ãģ¹ãģį
    -0.10
    è¿¢
    -0.10
    æ®·
    -0.10
    åħ¬åı¸å°Ĩ
    -0.09
    æĮ¯åħ´
    -0.09
    arrings
    -0.09
    è°Ł
    -0.09
    POSITIVE LOGITS
    2
    0.09
    5
    0.09
    htag
    0.08
    7
    0.08
    8
    0.08
    3
    0.08
    i
    0.08
    6
    0.08
    ย
    0.08
    4
    0.08
    Activations Density 0.282%

    No Known Activations