© 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. 62198
    Prev
    Next
    INDEX
    Explanations

    range and following words

    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
    éģ¿
    -0.11
    èĩĥ
    -0.11
    æ»ŀ
    -0.10
    çī¹ç§į
    -0.10
    åī©
    -0.10
    ruk
    -0.09
    èĭŁ
    -0.09
    èĦijæµ·ä¸Ń
    -0.09
    ä¾ĭå¤ĸ
    -0.09
    é¢Ĺç²Ĵ
    -0.09
    POSITIVE LOGITS
    ebra
    0.08
     tract
    0.08
     ì¤
    0.08
    æµģæ°´
    0.08
    åİķ
    0.08
    å¼Ģè¾Ł
    0.08
    çĺł
    0.08
    大大
    0.08
    aine
    0.08
    unk
    0.08
    Activations Density 0.051%

    No Known Activations