© 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. 17466
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transition 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
    å¿ĸ
    -0.11
    æıĨ
    -0.10
    å¬ĸ
    -0.10
    Statics
    -0.10
    èģ¿
    -0.09
    åīįä¸ĸ
    -0.09
    çĻ½äºij
    -0.09
    èĵĬ
    -0.09
    çĤ«
    -0.09
    éĨĩ
    -0.08
    POSITIVE LOGITS
    HIR
    0.09
    HN
    0.08
    æĺ¼å¤ľ
    0.08
    éĢĢ
    0.08
    让ä»ĸ们
    0.08
    ä¹Į
    0.08
    isz
    0.08
    æij½
    0.08
     instrumentation
    0.07
    oso
    0.07
    Activations Density 0.229%

    No Known Activations