© 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. 34419
    Prev
    Next
    INDEX
    Explanations

    phrase following "of"

    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
    åħ·ä½ĵæĥħåĨµ
    -0.10
    çī¹åĪ«
    -0.09
    estre
    -0.09
    иÑĤелÑĮн
    -0.09
    kus
    -0.09
    çī¹åĪ¥
    -0.08
    ç¡®åĪĩ
    -0.08
     specifics
    -0.08
    éĴı
    -0.08
    èij¶
    -0.08
    POSITIVE LOGITS
    åIJĦä½į
    0.10
    atten
    0.10
    åIJĦç±»
    0.10
    uden
    0.10
    èĩ³æĸ¼
    0.09
    æķĽ
    0.09
    äºĨä¸Ģéģį
    0.09
    åı¸
    0.09
    ARI
    0.09
    å¾Ģåīį
    0.09
    Activations Density 0.570%

    No Known Activations