© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20912
    Prev
    Next
    INDEX
    Explanations

    basal or basic start

    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
    liness
    -0.13
    ìĤ´
    -0.10
    ably
    -0.09
    ниÑĨа
    -0.09
    cation
    -0.09
    деÑģÑıÑĤ
    -0.09
    ingly
    -0.09
    visions
    -0.09
    vious
    -0.09
    nte
    -0.08
    POSITIVE LOGITS
    é¢ı
    0.12
    éĽĦåİļ
    0.12
     зн
    0.11
    ะ
    0.10
    иÑĢÑĥеÑĤÑģÑı
    0.10
    izza
    0.10
    èĩ¾
    0.09
    clang
    0.09
    ãĤĪãģĨãģª
    0.09
     Ñģвоей
    0.08
    Activations Density 0.045%

    No Known Activations