© 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. 20464
    Prev
    Next
    INDEX
    Explanations

    stoichiometric

    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
    sWith
    -0.10
    ular
    -0.10
    è´²
    -0.09
    دÙĪÙĦ
    -0.09
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    auge
    -0.08
    رÙĬ
    -0.08
    绳
    -0.08
    stage
    -0.08
    zug
    -0.08
    POSITIVE LOGITS
    ä¸Ģå®ļçļĦ
    0.10
    ftware
    0.10
    é¢ı
    0.10
    avage
    0.09
    iful
    0.09
    gether
    0.09
    è¡·
    0.09
    urma
    0.09
    обÑĢаз
    0.09
    obar
    0.09
    Activations Density 0.004%

    No Known Activations