© 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. 55980
    Prev
    Next
    INDEX
    Explanations

    used to followed by a verb

    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
    çĮĿ
    -0.10
    å¤ļå¹´æĿ¥
    -0.10
    èĴŁ
    -0.10
    åħ¶æīĢ
    -0.10
    strup
    -0.10
    诱
    -0.10
    ouse
    -0.10
    æľ¬æĿ¥å°±
    -0.09
    ãģ¾ãģ£ãģŁãģı
    -0.09
    ä»įæŧ
    -0.09
    POSITIVE LOGITS
    æĵĶå¿ĥ
    0.10
    -fashioned
    0.09
    urn
    0.09
     xuyên
    0.09
    uar
    0.08
    wick
    0.08
    æ´±
    0.08
    orks
    0.08
    ersh
    0.08
    aring
    0.08
    Activations Density 0.008%

    No Known Activations