© 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. 7183
    Prev
    Next
    INDEX
    Explanations

    emanating from glow

    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
    amar
    -0.10
    TING
    -0.09
    ãģĦãģĨ
    -0.09
    ãĥ£
    -0.09
     Graves
    -0.09
    grass
    -0.09
     Olympia
    -0.08
    ÙĤ
    -0.08
    شد
    -0.08
     Ñģобой
    -0.08
    POSITIVE LOGITS
    ingly
    0.12
     privileged
    0.10
    ÑĢÑĥд
    0.10
    headed
    0.10
    speaker
    0.10
    æ¦ľ
    0.10
    å½ĵãģ¦
    0.09
    orthy
    0.09
    常å§Ķ
    0.09
    ivent
    0.09
    Activations Density 0.001%

    No Known Activations