© 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. 10015
    Prev
    Next
    INDEX
    Explanations

    slide presentations

    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
    ted
    -0.12
    tings
    -0.11
    aceous
    -0.10
    ities
    -0.10
     виде
    -0.10
    TING
    -0.10
    ishment
    -0.10
    trag
    -0.09
    åĸª
    -0.09
    丧
    -0.09
    POSITIVE LOGITS
    hare
    0.11
    æĺī
    0.11
    hawk
    0.10
    éŃĦ
    0.09
    اÙĪ
    0.09
    ERING
    0.09
    guns
    0.09
    kick
    0.09
    iras
    0.08
    ularity
    0.08
    Activations Density 0.012%

    No Known Activations