© 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. 4526
    Prev
    Next
    INDEX
    Explanations

    other or such

    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
    ture
    -0.09
    å±¥
    -0.09
    _Log
    -0.09
    utters
    -0.09
    omics
    -0.09
    SError
    -0.08
    çı£
    -0.08
    ÑģÑĤи
    -0.08
    ernes
    -0.08
    楮
    -0.08
    POSITIVE LOGITS
     other
    0.28
    åħ¶ä»ĸ
    0.23
    åħ¶ä»ĸçļĦ
    0.21
    other
    0.21
    以åıĬåħ¶ä»ĸ
    0.20
    Other
    0.19
    ãģĿãģ®ä»ĸ
    0.19
     andere
    0.18
    _other
    0.18
    åħ¶å®ĥ
    0.18
    Activations Density 0.180%

    No Known Activations