© 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. 36300
    Prev
    Next
    INDEX
    Explanations

    booking form or table

    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
    åģİ
    -0.11
    à¹Į
    -0.11
    -0.10
    boro
    -0.10
    itious
    -0.09
    京津
    -0.09
    ophone
    -0.09
    ently
    -0.09
    èĪ°éĺŁ
    -0.09
     Ñĥд
    -0.08
    POSITIVE LOGITS
    uler
    0.09
    shelf
    0.09
    OrUpdate
    0.09
    acco
    0.08
    keeper
    0.08
     przecież
    0.08
    ©
    0.08
    keeping
    0.08
    леÑĢ
    0.08
    duk
    0.08
    Activations Density 0.006%

    No Known Activations