© 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. 11250
    Prev
    Next
    INDEX
    Explanations

    art education

    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
    utter
    -0.21
    umen
    -0.20
    æľºåŀĭ
    -0.20
    åĪĥ
    -0.19
    MISS
    -0.18
    acle
    -0.18
    ä¸Ī夫
    -0.18
    éĿŀæ³ķ
    -0.18
    -reader
    -0.17
    .NewReader
    -0.17
    POSITIVE LOGITS
    ç¾İæľ¯
    0.28
    çĶ»çĶ»
    0.26
    æ²¹çĶ»
    0.25
    åĪĽä½ľ
    0.25
    èīºæľ¯
    0.25
    ç»ĺçĶ»
    0.23
     Artists
    0.23
    审ç¾İ
    0.23
    /Graphics
    0.23
    (Canvas
    0.23
    Activations Density 0.024%

    No Known Activations