© 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. 62830
    Prev
    Next
    INDEX
    Explanations

    discounts or price reductions

    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
     thá»ijng
    -0.10
    hood
    -0.10
    檫
    -0.09
    rowse
    -0.09
    igner
    -0.09
    åįģä¸īæĿ¡
    -0.09
    oad
    -0.09
    读åIJİ
    -0.09
    å°±ç®Ĺæĺ¯
    -0.09
    ä¸Ńåħ³
    -0.09
    POSITIVE LOGITS
    enance
    0.14
    ably
    0.13
    ingly
    0.13
    edList
    0.11
    able
    0.10
    ieren
    0.10
    inue
    0.10
    arium
    0.10
    OrCreate
    0.09
    ariat
    0.09
    Activations Density 0.008%

    No Known Activations