© 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. 14686
    Prev
    Next
    INDEX
    Explanations

    danger danger danger danger danger danger danger danger danger danger

    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
     Moran
    -0.23
    nob
    -0.22
    å¹³æĿ¿
    -0.20
    defgroup
    -0.19
    elo
    -0.18
     Muss
    -0.18
    缴è¾ĸ
    -0.18
    ãģ«åħ¥ãģ£ãģ¦
    -0.18
     PERMISSION
    -0.18
     Malk
    -0.17
    POSITIVE LOGITS
    æĺİçŁ¥
    0.23
    #aa
    0.21
    _compat
    0.20
    èĭ£
    0.19
    ç§ĭåĨ¬
    0.19
    ings
    0.19
    (ang
    0.19
     Ñģвоими
    0.19
    åıĮèĦļ
    0.18
    ä»ĸ人
    0.18
    Activations Density 0.005%

    No Known Activations