© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 10501
    Prev
    Next
    INDEX
    Explanations

    `hashCode` or `Wilde`

    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
    Negative Logits
    为ä¼ģä¸ļ
    -0.18
     Laden
    -0.18
    çķ¸å½¢
    -0.18
    ä¸Ģ举
    -0.17
    çķ¸
    -0.17
    itore
    -0.17
    á»ħ
    -0.17
    icut
    -0.17
    颦
    -0.17
    çłĶ究æīĢ
    -0.17
    POSITIVE LOGITS
    rokes
    0.21
    å¢ī
    0.18
    å°ijå¹´
    0.18
    osite
    0.18
    æºľ
    0.18
    æ½¼
    0.17
    çĻ½å¤©
    0.17
    ByVersion
    0.17
    ç»ĵæĻ¶
    0.17
    attachment
    0.17
    Activations Density 0.001%

    No Known Activations