© 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. 29985
    Prev
    Next
    INDEX
    Explanations

    plan and strategy

    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
    ç®ķ
    -0.09
    åIJ¦
    -0.09
    è¯¥é¡¹çĽ®
    -0.08
    æĿ²
    -0.08
    æ§İ
    -0.08
    åľ°éģĵ
    -0.08
    enos
    -0.08
    ãĥ©ãĤ¤ãĥĪ
    -0.08
    STATUS
    -0.08
    符
    -0.08
    POSITIVE LOGITS
     plan
    0.17
    plan
    0.16
    -plan
    0.15
     план
    0.15
    计åĪĴ
    0.14
    Plan
    0.14
    è¡ĮåĬ¨è®¡åĪĴ
    0.13
     Plan
    0.13
    .plan
    0.13
    è¨ĪåĬĥ
    0.12
    Activations Density 0.036%

    No Known Activations