© 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. 36218
    Prev
    Next
    INDEX
    Explanations

    authors and science fiction

    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
     rou
    -0.10
    åį¬
    -0.09
    ä¸įåĪĨ
    -0.09
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    -0.09
    ĶĦ
    -0.08
    海峡
    -0.08
    _partner
    -0.08
    apus
    -0.08
     Taken
    -0.08
    伺
    -0.08
    POSITIVE LOGITS
    æĺŁéĻħ
    0.14
    ç§ijå¹»
    0.11
    é²Ľ
    0.10
    å¥ĩå¹»
    0.10
    èľļ
    0.10
    æ£ł
    0.09
    onaut
    0.09
    tright
    0.09
    çļĦè·Ŀ离
    0.09
    åŀ©
    0.09
    Activations Density 0.086%

    No Known Activations