© 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. 13015
    Prev
    Next
    INDEX
    Explanations

    all of global prevalence

    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
    åĺī宾
    -0.19
    atu
    -0.19
    æĺŁå·´
    -0.18
    setattr
    -0.18
    åİŁæłĩé¢ĺ
    -0.17
    æ¾İæ¹ĥæĸ°éĹ»
    -0.17
    .Conn
    -0.17
    uncate
    -0.17
    广çĶµ
    -0.17
    以便
    -0.17
    POSITIVE LOGITS
    çļĦ人éĥ½
    0.26
    ç»Ŀ大éĥ¨åĪĨ
    0.25
     fuss
    0.22
     halk
    0.21
    人éĥ½
    0.21
    ç»Ŀ大å¤ļæķ°
    0.20
    çµķ
    0.20
    åħ´æĹº
    0.20
    éĥ½æĺ¯
    0.20
    家ä¸Ń
    0.19
    Activations Density 0.111%

    No Known Activations