© 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. 31848
    Prev
    Next
    INDEX
    Explanations

    goo.gl links

    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
    ãģĵãģ¨
    -0.10
    ation
    -0.10
    ãģĦãģ¾ãģĻ
    -0.10
    nya
    -0.10
    sWith
    -0.10
    ness
    -0.10
    ÑĢеги
    -0.10
    ãģĦãģ¾ãģĻãģĮ
    -0.09
    sst
    -0.09
    chaft
    -0.09
    POSITIVE LOGITS
    er
    0.11
    -eyed
    0.09
    pty
    0.09
    erate
    0.09
    cks
    0.09
    nder
    0.09
    andi
    0.09
    羨
    0.09
    rink
    0.08
    æľĽåİ»
    0.08
    Activations Density 0.053%

    No Known Activations