© 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. 27082
    Prev
    Next
    INDEX
    Explanations

    steps, ramps, scale

    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
    ummies
    -0.10
    alah
    -0.09
    groupid
    -0.09
    èĩªä¹ł
    -0.09
    å¥Ĺè£ħ
    -0.09
    èĻŀ
    -0.09
    ional
    -0.09
    ç¼¢
    -0.09
    æ·³
    -0.09
    åıĹå½±åĵį
    -0.09
    POSITIVE LOGITS
    åŀ«
    0.13
    çŁ³
    0.10
    skip
    0.09
    åı°éĺ¶
    0.09
    ä¸įæĪIJ
    0.09
    stone
    0.09
    éĵºè®¾
    0.09
    è·¯éĿ¢
    0.09
     skip
    0.09
     quar
    0.08
    Activations Density 0.183%

    No Known Activations