© 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. 22064
    Prev
    Next
    INDEX
    Explanations

    URL, logo, Add, double, email, now

    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
    odore
    -0.09
    ResourceId
    -0.08
     бÑĭÑģÑĤÑĢо
    -0.08
    Spo
    -0.08
    WithName
    -0.08
    åĩij
    -0.08
    aurus
    -0.08
     spo
    -0.08
    íħĮ
    -0.08
    ADDR
    -0.08
    POSITIVE LOGITS
     SimpleName
    0.11
    ãģ¨åħ±
    0.10
    CURRENT
    0.09
    å¿ĥ缮
    0.08
    å¾Īå¼Ģå¿ĥ
    0.08
    çļĭ
    0.08
    <P
    0.08
    éĢłæĪIJ
    0.08
    ä¹ĭä½Ļ
    0.08
    å¾ĪæŃ£å¸¸
    0.08
    Activations Density 0.875%

    No Known Activations