© 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. 15654
    Prev
    Next
    INDEX
    Explanations

    right hand

    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
    èĢģ人家
    -0.22
    leine
    -0.19
     Mia
    -0.19
    à¸Ĺำà¸ģาร
    -0.18
    çĹŀ
    -0.18
    zza
    -0.18
    (insert
    -0.18
    èļĤ
    -0.17
     ordin
    -0.17
    ä¾ĽåĽ¾
    -0.17
    POSITIVE LOGITS
    令
    0.20
    Operand
    0.19
    STYPE
    0.19
    edu
    0.19
    enso
    0.19
    es
    0.19
    æķĻåŃ¦è´¨éĩı
    0.19
     Lair
    0.18
    Reviewer
    0.17
    èĻ
    0.17
    Activations Density 0.003%

    No Known Activations