© 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. 6690
    Prev
    Next
    INDEX
    Explanations

    starts with "a "

    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
    ses
    -0.13
    s
    -0.10
    å¨ĺå¨ĺ
    -0.09
    æIJª
    -0.09
    åĽŀ头çľĭ
    -0.09
    л
    -0.09
    lah
    -0.08
    ll
    -0.08
    sein
    -0.08
    t
    -0.08
    POSITIVE LOGITS
    ffect
    0.13
    arhus
    0.12
    usterity
    0.12
    æľĭåıĭ
    0.11
    ffects
    0.10
    æľªç»ı
    0.10
    VERAGE
    0.10
    lices
    0.10
    quate
    0.10
    alborg
    0.10
    Activations Density 0.324%

    No Known Activations