© 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. 22138
    Prev
    Next
    INDEX
    Explanations

    spelling and how words are written

    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
    imal
    -0.09
    #:
    -0.09
    atic
    -0.09
    aily
    -0.09
    æĥ³æ³ķ
    -0.09
    #{
    -0.08
    allah
    -0.08
    寡
    -0.08
    设
    -0.08
     Strauss
    -0.08
    POSITIVE LOGITS
     spelled
    0.15
     spelling
    0.13
     spell
    0.12
    æĭ¼éŁ³
    0.11
    Spell
    0.10
    spell
    0.10
     Spell
    0.10
     spells
    0.10
     Nä
    0.10
    ings
    0.10
    Activations Density 0.012%

    No Known Activations