© 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. 14720
    Prev
    Next
    INDEX
    Explanations

    years, numbers

    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
    trail
    -0.19
     SOP
    -0.19
    æĢĢçĿĢ
    -0.19
    stype
    -0.18
    _fx
    -0.18
    çĶļèĩ³æĺ¯
    -0.18
    åij¨æľ«
    -0.18
    ç²¾åĵģ
    -0.17
    çĶļèĩ³è¿ŀ
    -0.17
    饶
    -0.17
    POSITIVE LOGITS
    ä¸ĭ称
    0.19
    çĺª
    0.19
    val
    0.19
    å¤©çľŁ
    0.18
     wool
    0.18
    uli
    0.18
    cid
    0.18
    åį«
    0.17
     wÅĤ
    0.17
    èĹ»
    0.17
    Activations Density 0.016%

    No Known Activations