© 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. 56327
    Prev
    Next
    INDEX
    Explanations

    due to the nature of

    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
    å¾Ĺ以
    -0.08
    è§ĨåĬĽ
    -0.08
    isms
    -0.08
    说å¾Ĺ
    -0.08
     Hag
    -0.08
    åı¯éĿłçļĦ
    -0.07
    æºī
    -0.07
    å¼Ĥ
    -0.07
    æĻºæħ§åŁİå¸Ĥ
    -0.07
    Equivalent
    -0.07
    POSITIVE LOGITS
     nature
    0.23
    nature
    0.20
    æĢ§è´¨
    0.17
    Nature
    0.16
     Nature
    0.15
    大èĩªçĦ¶
    0.12
     natur
    0.11
    èĩªçĦ¶çķĮ
    0.10
    æĺ¯éŁ©åĽ½
    0.10
    绶
    0.10
    Activations Density 0.062%

    No Known Activations