© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10456
    Prev
    Next
    INDEX
    Explanations

    have + [past participle/state]

    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
    ünde
    -0.11
    亨
    -0.10
    çĶ¨å¿ĥ
    -0.10
    éĦ¯
    -0.09
    omaly
    -0.08
     ineligible
    -0.08
    åįİå°Ķ
    -0.08
    atte
    -0.08
    ASTER
    -0.08
    rio
    -0.08
    POSITIVE LOGITS
    ä¸Ĭåİ»
    0.09
    ä¸Ģ缴
    0.09
    éĩijåŃĹ
    0.09
    èĮĥ
    0.09
    ä¸Ģ大åłĨ
    0.09
    åħ³éĶ®åŃĹ
    0.08
    åįĩåįİ
    0.08
    backs
    0.08
    为ä¹ĭ
    0.08
    ä¸Ģ缴éĥ½æĺ¯
    0.08
    Activations Density 0.023%

    No Known Activations