© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15365
    Prev
    Next
    INDEX
    Explanations

    deals and coupons

    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
    alk
    -0.20
     Eig
    -0.20
     parts
    -0.20
     Kimber
    -0.19
     DNA
    -0.19
     UNESCO
    -0.19
    Surname
    -0.19
    端æŃ£
    -0.19
    åĪĽä½ľ
    -0.19
    .parts
    -0.18
    POSITIVE LOGITS
    å®ŀæŶ
    0.30
    ãĤŃãĥ£ãĥ³ãĥļ
    0.26
    åĩºåĩ»
    0.25
    æĬĺæī£
    0.24
    ãģĬãģĻãģĻ
    0.24
     coupons
    0.24
    geber
    0.24
    æĪIJåĬŁçİĩ
    0.23
    çĽ¯
    0.23
    æĭīåĬ¨
    0.23
    Activations Density 0.032%

    No Known Activations