© 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. 5253
    Prev
    Next
    INDEX
    Explanations

    some thing

    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
    åĩºå¤Ħ
    -0.09
    çĹ¹
    -0.09
    æªĢ
    -0.08
    acious
    -0.08
    _cm
    -0.08
     McA
    -0.08
    ergarten
    -0.07
    elman
    -0.07
    éĢŁ
    -0.07
    æľĢå¿«çļĦ
    -0.07
    POSITIVE LOGITS
    ä¸ĭåįĬ
    0.11
    èį¦
    0.11
    å°§
    0.10
    衾
    0.10
    çĶŁäº§èĥ½åĬĽ
    0.09
    å¼¥
    0.09
    èı½
    0.09
    æ¹
    0.09
    кÑĢаÑĤ
    0.09
    виз
    0.09
    Activations Density 0.201%

    No Known Activations