© 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. 3438
    Prev
    Next
    INDEX
    Explanations

    mockery, mockist, mockito, mock spawn

    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
    ниÑĩ
    -0.11
    icolor
    -0.10
    éļħ
    -0.10
    .linkedin
    -0.09
     оÑĤз
    -0.09
    ìº
    -0.09
    agal
    -0.08
    iska
    -0.08
    ä¸įæĺĵ
    -0.08
    åħ¬è®¤çļĦ
    -0.08
    POSITIVE LOGITS
    ito
    0.13
    ingly
    0.13
    intosh
    0.11
    inary
    0.10
    uments
    0.09
    busters
    0.09
    ness
    0.09
    ../../../
    0.09
    town
    0.09
    uary
    0.09
    Activations Density 0.014%

    No Known Activations