© 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. 62259
    Prev
    Next
    INDEX
    Explanations

    potential or possibility

    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
    çĸ£
    -0.08
    容
    -0.08
    缺å¸Ń
    -0.08
    åĬ£
    -0.07
    .quit
    -0.07
    diff
    -0.07
    åĸĦèī¯
    -0.07
     ëį
    -0.07
    .NewReader
    -0.07
    ä¿¡ä»»
    -0.07
    POSITIVE LOGITS
     possibility
    0.16
     potential
    0.16
    æ½ľåľ¨
    0.15
    æľīåı¯èĥ½
    0.15
    potential
    0.13
     Potential
    0.12
    Potential
    0.12
     possibilitÃł
    0.12
    æľīæľºä¼ļ
    0.11
    æ½ľåĬĽ
    0.11
    Activations Density 0.070%

    No Known Activations