© 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. 10555
    Prev
    Next
    INDEX
    Explanations

    flickering

    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
    abouts
    -0.10
    pir
    -0.09
    ooter
    -0.09
    onest
    -0.09
    ück
    -0.09
    æį¶
    -0.09
    åŁĤ
    -0.09
    èĮ«èĮ«
    -0.09
    ayout
    -0.09
    ä½Ŀ
    -0.09
    POSITIVE LOGITS
    å±±åºĦ
    0.10
    ering
    0.10
    elly
    0.10
    ett
    0.10
    et
    0.09
    etur
    0.09
    arger
    0.09
    èĩªå¦Ĥ
    0.09
    rov
    0.08
    urious
    0.08
    Activations Density 0.004%

    No Known Activations