© 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. 57891
    Prev
    Next
    INDEX
    Explanations

    Joomla framework code

    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
    Oregon
    -0.10
     Dre
    -0.09
    conj
    -0.09
    æĻı
    -0.09
    æĶ»åĬ¿
    -0.09
    å¤Ħå¤Ħ
    -0.09
    为人
    -0.09
    è·ŁæĪij
    -0.09
    Colorado
    -0.08
    æŃ¥è¡Į
    -0.08
    POSITIVE LOGITS
     Joomla
    0.10
    erek
    0.08
    èĤ²
    0.08
    顯
    0.08
    æĺ¾
    0.08
    _ticks
    0.08
    æ²Ł
    0.08
    stein
    0.08
    quiring
    0.08
     JText
    0.08
    Activations Density 0.065%

    No Known Activations