© 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. 12891
    Prev
    Next
    INDEX
    Explanations

    expert feedback and reviews

    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
    OMEM
    -0.23
    AFE
    -0.20
    еÑĩа
    -0.20
    CppType
    -0.20
    åħ¨åªĴä½ĵ
    -0.19
     ÑĢеÑģÑĤ
    -0.18
    CCA
    -0.18
    AMED
    -0.18
     distress
    -0.18
    alone
    -0.17
    POSITIVE LOGITS
    å®¡æł¸
    0.28
    认åı¯
    0.26
    Reviewer
    0.24
    å®¡æŁ¥
    0.24
    çĤ¹è¯Ħ
    0.23
    è¯Ħä»·
    0.23
    æĦıè§ģ
    0.23
    è¯Ħ审
    0.23
    ãĤ³ãĥ¡ãĥ³ãĥĪ
    0.23
    审æī¹
    0.23
    Activations Density 0.110%

    No Known Activations