© 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. 19259
    Prev
    Next
    INDEX
    Explanations

    problem with

    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
    uant
    -0.09
    ÑĢаж
    -0.09
    nda
    -0.09
    вел
    -0.09
    ITAL
    -0.09
    uje
    -0.08
    TING
    -0.08
    coder
    -0.08
    ear
    -0.08
    erate
    -0.08
    POSITIVE LOGITS
    ática
    0.13
    atica
    0.12
    atic
    0.12
    atics
    0.12
    ä¸Ģ个éĹ®é¢ĺ
    0.12
    atical
    0.11
    _CBC
    0.11
    atically
    0.11
    ATIC
    0.10
    atisch
    0.10
    Activations Density 0.113%

    No Known Activations