© 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. 16127
    Prev
    Next
    INDEX
    Explanations

    north of

    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
    á¿ĸ
    -0.21
    éŁŃèıľ
    -0.19
     Hew
    -0.18
    /stat
    -0.18
    å´ĥ
    -0.18
    èĴĮ
    -0.17
    .gz
    -0.17
    plies
    -0.17
    éĶ¤
    -0.17
    .Safe
    -0.17
    POSITIVE LOGITS
    æ°¸ä¹ħ
    0.24
    à¸Ĥà¸Ļ
    0.21
    å¥ĩå¼Ĥ
    0.21
    ä¸ī大
    0.20
    onto
    0.20
    ãģĭãģ¤
    0.20
    亩
    0.20
    èĩªçĦ¶
    0.20
    æ°¸æģĴ
    0.20
    VF
    0.20
    Activations Density 0.037%

    No Known Activations