© 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. 47794
    Prev
    Next
    INDEX
    Explanations

    setting system paths and variables

    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
    pcm
    -0.09
    ç³Ļ
    -0.09
    ç´§å¯Ĩ
    -0.08
    æµ·å²Ľ
    -0.08
    åĶ¯
    -0.08
    å«Į
    -0.08
    ç®Ĺ
    -0.08
    å¼±çĤ¹
    -0.08
    è¿ľæ´ĭ
    -0.08
    éļ¾åº¦
    -0.08
    POSITIVE LOGITS
    GOR
    0.11
     PATH
    0.10
    çĵ¦
    0.09
    uly
    0.09
    incer
    0.09
    ÑĥÑģ
    0.08
    _paths
    0.08
    åľ¨åĵª
    0.08
    å±Ī
    0.08
    extras
    0.08
    Activations Density 0.235%

    No Known Activations