© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7371
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    èıľ
    -0.10
    ç¹ŀ
    -0.09
    ç»ķ
    -0.09
    åĽ´
    -0.09
    åľ¨éĩĮéĿ¢
    -0.09
    çªĹå¸ĺ
    -0.09
    çĹĺ
    -0.08
    spiel
    -0.08
    åĮħåĽ´
    -0.08
    æĹĭ
    -0.08
    POSITIVE LOGITS
    æĥ³çĿĢ
    0.09
    æѧ
    0.09
    æīĵå¾Ĺ
    0.08
    æ³µ
    0.08
    çºłæŃ£
    0.08
    SCP
    0.08
    TEM
    0.08
    OperationException
    0.08
    olate
    0.08
    åIJ¸åıĸ
    0.08
    Activations Density 0.073%

    No Known Activations