© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 18404
    Prev
    Next
    INDEX
    Explanations

    pixel Dungeon / display / lenses / TV

    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
    sWith
    -0.10
    ance
    -0.09
    ryn
    -0.09
    atted
    -0.09
     vic
    -0.08
    æĢį
    -0.08
    çī©èµĦ
    -0.08
    xi
    -0.08
    éļħ
    -0.08
    yard
    -0.08
    POSITIVE LOGITS
    abay
    0.13
    hawk
    0.10
    hoot
    0.09
    olare
    0.09
    scoped
    0.09
     Mits
    0.09
    รวà¸Ķ
    0.09
    atori
    0.08
    _Params
    0.08
    phia
    0.08
    Activations Density 0.017%

    No Known Activations