© 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. 1248
    Prev
    Next
    INDEX
    Explanations

    delivered almonds

    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
    åıijåĬ¨
    -0.10
    çŁ¥éģĵäºĨ
    -0.10
    åŀ¢
    -0.09
    转载请
    -0.09
    éļIJèĶ½
    -0.09
    æĹłåģ¿
    -0.09
    æ·Ģ
    -0.08
    åłĥ
    -0.08
    帮ä»ĸ
    -0.08
    çĦĸ
    -0.08
    POSITIVE LOGITS
    lef
    0.09
    èµ·çĤ¹
    0.09
    _MOV
    0.08
    usz
    0.08
     Sheila
    0.08
    åħ¸åŀĭçļĦ
    0.08
    ucer
    0.08
    èµ°åIJij
    0.08
    richt
    0.08
    BAT
    0.08
    Activations Density 0.002%

    No Known Activations