© 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. 53658
    Prev
    Next
    INDEX
    Explanations

    prerequisite/requisite for

    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
    aceous
    -0.10
    ished
    -0.10
    ersion
    -0.09
     подÑĢоб
    -0.09
    æĮ£æīİ
    -0.09
    /we
    -0.09
    yna
    -0.09
    ละ
    -0.09
    еÑĢж
    -0.08
    oved
    -0.08
    POSITIVE LOGITS
    zes
    0.09
    éĩįéĩį
    0.09
    ively
    0.08
    roz
    0.08
    _markup
    0.08
    yz
    0.08
    -taking
    0.08
    zd
    0.08
     Mary
    0.08
    ves
    0.08
    Activations Density 0.009%

    No Known Activations