© 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. 36441
    Prev
    Next
    INDEX
    Explanations

    what will you be doing

    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
    åĿij
    -0.09
    ç»İ
    -0.08
     rev
    -0.08
    bye
    -0.08
    wich
    -0.08
     Saras
    -0.08
     Rev
    -0.08
    追
    -0.08
    æīĵåĩº
    -0.08
    LG
    -0.08
    POSITIVE LOGITS
    å«ļ
    0.12
    ä¸Ń举
    0.11
    çĽ¼
    0.10
     ballo
    0.10
    åıįå¼¹
    0.10
    æĶ¾å¼ĥäºĨ
    0.10
    çĽ¸å¹²
    0.10
    OperationException
    0.09
    æ²ĵ
    0.09
    /frontend
    0.09
    Activations Density 0.033%

    No Known Activations