© 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. 1177
    Prev
    Next
    INDEX
    Explanations

    single [noun/adjective] + [noun]

    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
     вÑģего
    -0.10
    èĭ¥å¹²
    -0.09
    ammer
    -0.08
    æī¾å·¥ä½ľ
    -0.08
    ức
    -0.08
    wart
    -0.08
    åIJ¬çĿĢ
    -0.08
    eld
    -0.08
    dam
    -0.07
    Hierarchy
    -0.07
    POSITIVE LOGITS
    itarian
    0.11
    æĪĸå¤ļ
    0.11
     лиÑĪÑĮ
    0.11
    æ¹¾åĮº
    0.10
    tons
    0.10
    åİļåİļçļĦ
    0.10
    åįłæį®
    0.10
    aho
    0.10
    ãģĦãĤĭ
    0.10
    icit
    0.09
    Activations Density 0.025%

    No Known Activations