© 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. 11965
    Prev
    Next
    INDEX
    Explanations

    nik or vik names

    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
    ãģĩ
    -0.11
    èĩ¾
    -0.10
    ×ķת
    -0.10
    erm
    -0.10
    ipt
    -0.09
    est
    -0.09
    nut
    -0.09
    ÂŃing
    -0.09
    iro
    -0.09
    ses
    -0.08
    POSITIVE LOGITS
    们
    0.11
    peare
    0.11
    лÑİд
    0.10
    .forRoot
    0.10
    emes
    0.10
    ©
    0.10
    osis
    0.09
    yla
    0.09
    âĶŀ
    0.09
    InteractionEnabled
    0.09
    Activations Density 0.072%

    No Known Activations