© 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. 38611
    Prev
    Next
    INDEX
    Explanations

    investment adviser and fiduciary duty

    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
    æŁĶæĢ§
    -0.10
    ifo
    -0.09
     Bihar
    -0.09
    å®ł
    -0.09
    çĶŁèĤ²
    -0.09
    iant
    -0.09
    çķĮéĿ¢
    -0.09
    ione
    -0.08
    .bat
    -0.08
     assignable
    -0.08
    POSITIVE LOGITS
    fid
    0.09
    afil
    0.09
    (fid
    0.09
    é²ľ
    0.09
     fid
    0.09
     Hazel
    0.09
    çĻ»ä¸Ĭ
    0.09
    æ±Łå±±
    0.09
    å®Ĺ
    0.09
    éľ²
    0.08
    Activations Density 0.104%

    No Known Activations