© 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. 10803
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    resh
    -0.21
    ä¸ĢçĤ¹çĤ¹
    -0.19
    å¸ĪåĤħ
    -0.19
    çķ¥
    -0.19
    ä¸ĢçĤ¹
    -0.19
    ä¹ĭåĪĿ
    -0.19
    acct
    -0.18
    Spo
    -0.18
    nda
    -0.18
    incer
    -0.17
    POSITIVE LOGITS
    éķŃ
    0.20
     hamm
    0.20
    ertz
    0.19
    åıĬ缸åħ³
    0.18
    æ»´
    0.18
    iliar
    0.18
    åħ¨æµģç¨ĭ
    0.18
    æ¼Ķåĩº
    0.18
    éŁ³
    0.18
     graphic
    0.18
    Activations Density 0.004%

    No Known Activations