© 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. 11416
    Prev
    Next
    INDEX
    Explanations

    price or prices

    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
    ness
    -0.12
    lah
    -0.12
    rece
    -0.10
    еÑĢе
    -0.10
    ships
    -0.10
    ÑĢеÑĪ
    -0.10
    à¹Į
    -0.09
     пÑĢава
    -0.09
    ìĤ¬íķŃ
    -0.09
    quist
    -0.09
    POSITIVE LOGITS
    holders
    0.10
    gap
    0.09
    åħ±åIJĮä½ĵ
    0.09
    åIJĦå¼Ĥ
    0.08
    åĪ¶åº¦æĶ¹éĿ©
    0.08
    éĴµ
    0.08
    finder
    0.08
    缸è¿ij
    0.08
    ç°¿
    0.08
     trá»ĭ
    0.08
    Activations Density 0.022%

    No Known Activations