© 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. 4863
    Prev
    Next
    INDEX
    Explanations

    Google, .co, .uk

    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
    è·¨è¶Ĭ
    -0.08
    _CLI
    -0.08
     Intercept
    -0.08
    -php
    -0.08
    _VERBOSE
    -0.08
    _INITIALIZ
    -0.08
    ATAB
    -0.08
    æŃ£æĸĩ
    -0.08
    缮åħī
    -0.08
    POSITIVE LOGITS
    åıijå±ķè¶ĭåĬ¿
    0.10
    ippy
    0.09
    çĹħåĽł
    0.09
    ç»ıæµİåѦ
    0.09
    é£İæ°´
    0.09
    åĸľæ¬¢åIJĥ
    0.09
    伪éĢł
    0.08
    åī½
    0.08
    æĺ¯æľĢ好çļĦ
    0.08
    认为
    0.08
    Activations Density 0.329%

    No Known Activations