© 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. 56371
    Prev
    Next
    INDEX
    Explanations

    nut and nuts

    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
    éĺŁ
    -0.10
    æ±°
    -0.09
     Sands
    -0.09
     Herb
    -0.09
    lar
    -0.09
    ût
    -0.09
    çģ¶
    -0.09
    èģĨåIJ¬
    -0.09
    çĸŁ
    -0.09
    hone
    -0.08
    POSITIVE LOGITS
    åĿļæŀľ
    0.12
     nuts
    0.10
    ç¢İ
    0.09
    举
    0.09
    æĺ¯å¯¹
    0.09
     impression
    0.09
     bor
    0.09
    bor
    0.09
    ä¸ĩåı°
    0.09
     nut
    0.08
    Activations Density 0.206%

    No Known Activations