© 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. 6404
    Prev
    Next
    INDEX
    Explanations

    high, activity, effects

    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
    .matrix
    -0.10
    沧
    -0.10
    笼
    -0.10
    顺åºĶ
    -0.09
    庸
    -0.09
    åĩĨ
    -0.08
    .headers
    -0.08
    å´´
    -0.08
    é¢Ĩ
    -0.08
     Lesb
    -0.08
    POSITIVE LOGITS
    çĻ«
    0.11
    åħ´å¥ĭ
    0.11
    çĸ¯
    0.10
    çĭĤ
    0.10
    æ¾İæ¹ĥ
    0.10
    çĺĭ
    0.10
    çĦ¦èĻij
    0.10
    çĸ¯çĭĤ
    0.09
    agger
    0.09
     bip
    0.09
    Activations Density 0.080%

    No Known Activations