© 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. 3807
    Prev
    Next
    INDEX
    Explanations

    Missouri and Mo

    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
    EDIA
    -0.09
    íij¸
    -0.08
    DebugEnabled
    -0.08
    èĽĻ
    -0.08
    лаг
    -0.08
    饱
    -0.08
    apan
    -0.08
    unde
    -0.08
    ameron
    -0.08
     PRIV
    -0.08
    POSITIVE LOGITS
    enance
    0.11
    jin
    0.10
    matic
    0.09
    heim
    0.09
    æĻ°
    0.09
    xious
    0.08
    и
    0.08
    ä¸Ĭåīį
    0.08
    iguous
    0.08
    ument
    0.08
    Activations Density 0.013%

    No Known Activations