© 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. 17400
    Prev
    Next
    INDEX
    Explanations

    packaging, equipment, patent, javascript

    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
    è¶Ł
    -0.10
    线
    -0.09
    éī´
    -0.09
    åĬ¿
    -0.08
    è¿ľå¤Ħ
    -0.08
     Executors
    -0.08
     дл
    -0.08
    踵
    -0.08
    _extend
    -0.08
    é¢ijçİĩ
    -0.08
    POSITIVE LOGITS
    èĪ±
    0.13
    ä½ĵåĪ¶æľºåĪ¶
    0.11
    usc
    0.10
    èķ¤
    0.10
    çģ«çĤ¬
    0.09
    çĪ±ç¾İ
    0.09
    åħļçļĦ建设
    0.09
    aps
    0.09
    èī
    0.09
    çµIJæ§ĭ
    0.09
    Activations Density 0.149%

    No Known Activations