© 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. 31209
    Prev
    Next
    INDEX
    Explanations

    University names and colleges

    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
    åĺ»
    -0.10
    Knight
    -0.10
    sell
    -0.09
    วา
    -0.09
    arris
    -0.09
    帳
    -0.08
     EAR
    -0.08
    duk
    -0.08
    reo
    -0.08
    engo
    -0.08
    POSITIVE LOGITS
    饿
    0.10
    é»ijçĻ½
    0.09
    äºĭåıij
    0.09
    æ¾į
    0.08
    ç®Ģ称
    0.08
     обÑĭ
    0.08
    åį³ä¾¿
    0.08
    UC
    0.08
    æ²£
    0.08
    åĬ³åĬ¨
    0.07
    Activations Density 0.033%

    No Known Activations