© 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. 33144
    Prev
    Next
    INDEX
    Explanations

    oreo, Oregen, Orecchia, orellanus

    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
    alic
    -0.09
    LLU
    -0.09
    åŀĤ
    -0.09
    æĥ¯
    -0.08
    annon
    -0.08
    Êĥ
    -0.08
    åīģ
    -0.08
    jÄħ
    -0.08
    æĪĸå¤ļ
    -0.08
    诩
    -0.08
    POSITIVE LOGITS
     Tos
    0.10
    ITAL
    0.09
    çĹĽçĤ¹
    0.09
     factory
    0.09
     Queens
    0.09
    沸
    0.09
    å·¥åİĤ
    0.08
    å¢ī
    0.08
     tumble
    0.08
    ä¸Ńéĥ¨
    0.08
    Activations Density 0.002%

    No Known Activations