© 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. 12983
    Prev
    Next
    INDEX
    Explanations

    equations with variables

    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
    æ¼ī
    -0.22
     Yak
    -0.21
    ä½Ĺ
    -0.18
    ce
    -0.18
     Jaime
    -0.18
    esto
    -0.17
    ero
    -0.17
    lo
    -0.17
    ERO
    -0.17
    ials
    -0.16
    POSITIVE LOGITS
    jsc
    0.19
    ynes
    0.19
    phia
    0.18
    çŃīçŃī
    0.18
    温馨
    0.18
    PointerType
    0.18
    ounder
    0.18
    овал
    0.17
    ouses
    0.17
    èĩªçĦ¶
    0.17
    Activations Density 0.070%

    No Known Activations