© 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. 39750
    Prev
    Next
    INDEX
    Explanations

    Stewart

    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
    -0.14
    usz
    -0.11
    åīįæīĢ
    -0.11
    etic
    -0.11
    ning
    -0.10
    ãĤĥ
    -0.09
    oust
    -0.09
    etically
    -0.09
    odi
    -0.09
    çŁ¥éģĵèĩªå·±
    -0.09
    POSITIVE LOGITS
    ¹
    0.12
    ÑĤиÑĢ
    0.11
    ÑĢ
    0.10
    ãĢħ
    0.10
    avel
    0.10
    ÑģÑı
    0.09
    è¯Ľ
    0.09
    aining
    0.09
    ãģ¹ãģį
    0.09
    fried
    0.09
    Activations Density 0.010%

    No Known Activations