© 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. 50505
    Prev
    Next
    INDEX
    Explanations

    Chamber of Commerce, events, Orchestra

    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
    sert
    -0.10
    -0.10
    ammen
    -0.10
    atron
    -0.09
    oris
    -0.09
    oward
    -0.09
    æ¤ħ
    -0.09
     Diá»ħn
    -0.09
    igy
    -0.09
    enance
    -0.09
    POSITIVE LOGITS
    lain
    0.18
    ties
    0.13
    maid
    0.12
    ize
    0.10
    hips
    0.10
    mates
    0.10
    forth
    0.10
    riers
    0.10
    cade
    0.10
    ãģĹãģ¾ãģĨ
    0.10
    Activations Density 0.013%

    No Known Activations