© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50597
    Prev
    Next
    INDEX
    Explanations

    television series Battlestar Galactica

    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
    æĩĭ
    -0.11
    zte
    -0.10
    å£ģ纸
    -0.10
     luáºŃt
    -0.10
    UBL
    -0.09
    æĺŁæľŁ
    -0.09
    ç¦ģ
    -0.09
    zion
    -0.09
    hte
    -0.09
    èĥĮåıĽ
    -0.09
    POSITIVE LOGITS
    æįŁ
    0.09
    éªĬ
    0.09
     Meg
    0.08
    ç°ĭ
    0.08
    é»ij马
    0.08
    çģ«å±±
    0.08
     Barg
    0.08
    马æĭīæĿ¾
    0.08
    éĿ¢åĮħ
    0.08
    знак
    0.08
    Activations Density 0.035%

    No Known Activations