© 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. 54187
    Prev
    Next
    INDEX
    Explanations

    stock price or inventory

    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
    æ´İ
    -0.09
    orage
    -0.09
    æĢİ
    -0.09
    ãģ«ãģªãĤĭãģ¨
    -0.08
    å®īæ£Ģ
    -0.08
    æį·
    -0.08
    .utf
    -0.08
    زاÙĨ
    -0.08
    oded
    -0.08
    è¶ĭ
    -0.08
    POSITIVE LOGITS
    pile
    0.15
    holders
    0.12
    piler
    0.11
    ier
    0.11
    manship
    0.10
    (stock
    0.09
    PILE
    0.09
    åĬ©éķ¿
    0.09
    inged
    0.09
    man
    0.09
    Activations Density 0.024%

    No Known Activations