© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14119
    Prev
    Next
    INDEX
    Explanations

    hesitate, hesitant, hesitation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    躺çĿĢ
    -0.21
    stead
    -0.20
    åŃ¦å®¶
    -0.19
    PLE
    -0.18
    éĵĽ
    -0.17
    inez
    -0.17
    .Flags
    -0.17
    å¯ĤéĿĻ
    -0.17
    åѦåĪ°
    -0.16
    å§ĭç»Īä¿ĿæĮģ
    -0.16
    POSITIVE LOGITS
    official
    0.21
    éĩįéĩį
    0.20
    overs
    0.19
    çĶļèĩ³
    0.19
    人éĢī
    0.18
    lected
    0.18
    oka
    0.18
    ðŁı»
    0.18
     Salem
    0.17
    ä½ıäºĨ
    0.17
    Activations Density 0.009%

    No Known Activations