© 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. 22730
    Prev
    Next
    INDEX
    Explanations

    never + 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
    åĽĽå¤Ħ
    -0.08
     Colony
    -0.08
    enberg
    -0.08
    illion
    -0.08
    venues
    -0.08
    undred
    -0.08
    缮åīįå·²
    -0.08
    èıģ
    -0.08
    ince
    -0.08
    nell
    -0.08
    POSITIVE LOGITS
    æľīæīĢ
    0.10
    å®ķ
    0.09
    ç¼Ń
    0.09
    å´Ĩ
    0.09
    个å¤ļ
    0.09
    æĬĬè¿Ļ个
    0.08
    çĸijéļ¾
    0.08
    ä¸Ģä¸ĭåŃIJ
    0.08
    è·Łä¸įä¸Ĭ
    0.08
    åħ·ä½ĵæĥħåĨµ
    0.08
    Activations Density 0.017%

    No Known Activations