© 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. 30673
    Prev
    Next
    INDEX
    Explanations

    llc, llvm, llambda, genotype

    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
    溷
    -0.10
    irement
    -0.09
    etti
    -0.09
    管çIJĨåĬŀæ³ķ
    -0.09
    æľįåĬ¡å¹³åı°
    -0.08
     lá»Ĺi
    -0.08
    åĨķ
    -0.08
    æģĥ
    -0.08
    orbit
    -0.08
    ë¡Ń
    -0.08
    POSITIVE LOGITS
    ustr
    0.12
    igator
    0.11
    agoon
    0.10
    rench
    0.10
    8
    0.10
    7
    0.10
    ãģ£ãģ±
    0.09
    ancy
    0.09
    3
    0.09
    æĭĺ
    0.09
    Activations Density 0.044%

    No Known Activations