© 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. 47842
    Prev
    Next
    INDEX
    Explanations

    group member

    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
    оÐ
    -0.09
    opi
    -0.09
    æ²Ķ
    -0.08
    åĨł
    -0.08
    gis
    -0.08
    åħ¶æīĢ
    -0.08
    æĶ¹éĿ©åıijå±ķ
    -0.08
     ЮÑĢ
    -0.08
    éĢł
    -0.08
    ë¡Ŀ
    -0.08
    POSITIVE LOGITS
    æĪIJåijĺ
    0.27
     members
    0.19
     member
    0.17
    人åijĺ
    0.16
    member
    0.15
    members
    0.15
    _member
    0.14
    ãĥ¡ãĥ³ãĥIJãĥ¼
    0.14
    -member
    0.13
     Members
    0.13
    Activations Density 0.091%

    No Known Activations