© 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. 52708
    Prev
    Next
    INDEX
    Explanations

    Latin-based language word endings

    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
    oving
    -0.08
    time
    -0.07
     same
    -0.07
     оÑĤд
    -0.07
    lox
    -0.07
     hon
    -0.07
    cg
    -0.07
    phone
    -0.07
    举
    -0.07
    y
    -0.07
    POSITIVE LOGITS
    Äĩi
    0.09
    ãĥŀãĥ³
    0.09
    éļ¾æ°ij
    0.09
     eks
    0.09
    詹
    0.09
    TriState
    0.09
    åħħ满äºĨ
    0.09
    éĤł
    0.09
    åį¡è½¦
    0.09
    DisplayStyle
    0.09
    Activations Density 0.223%

    No Known Activations