© 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. 14357
    Prev
    Next
    INDEX
    Explanations

    joining or buying into ideas

    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
    åĬ¬
    -0.20
    scopes
    -0.20
    èĨ³
    -0.20
    çķĻç»Ļ
    -0.19
    åı²æĸĻ
    -0.18
    .cmd
    -0.18
    ivos
    -0.17
    ç©¿
    -0.17
     czÄĻ
    -0.17
    lijk
    -0.17
    POSITIVE LOGITS
     idea
    0.29
     ideas
    0.27
    ideas
    0.23
    çļĦçIJĨ念
    0.23
    çIJĨ念
    0.22
     Ideas
    0.22
     notions
    0.22
    认为
    0.21
    æĥ³æ³ķ
    0.21
    æ¦Ĥ念
    0.20
    Activations Density 0.023%

    No Known Activations