© 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. 34901
    Prev
    Next
    INDEX
    Explanations

    featuring or features

    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
    èĤ¡
    -0.10
    åĴ¸
    -0.09
    èĢģé¾Ħ
    -0.08
    pher
    -0.08
    í
    -0.08
    ãģĨãģ¡
    -0.08
    andid
    -0.08
    ÑĢÑĥз
    -0.08
    elas
    -0.08
     Subcommittee
    -0.08
    POSITIVE LOGITS
    èľĺèĽĽ
    0.10
    天使
    0.09
    说æľį
    0.09
    æī¹åıij
    0.08
    è¯Ľ
    0.08
    ä»»
    0.08
    äºĽè®¸
    0.08
    -desc
    0.08
    èı©æıIJ
    0.08
    éĵ¶æ²³
    0.08
    Activations Density 0.013%

    No Known Activations