© 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. 16057
    Prev
    Next
    INDEX
    Explanations

    goal, intention, or challenge

    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
    ohl
    -0.20
     ÑĢазлиÑĩнÑĭе
    -0.20
    åĴĮåľ°åĮº
    -0.19
    è§ģè¯ģ
    -0.18
    æ²»çIJĨä½ĵç³»
    -0.18
    rep
    -0.17
    ðŁĺĵ
    -0.17
    ailles
    -0.17
    croll
    -0.17
    _INLINE
    -0.17
    POSITIVE LOGITS
    åľ¨äºİ
    0.37
    å°±åľ¨äºİ
    0.36
    å°±æĺ¯è¦ģ
    0.32
    缮çļĦæĺ¯
    0.31
    æĺ¯è¦ģ
    0.30
     aim
    0.30
    çļĦæĺ¯
    0.27
    çļĦå°±æĺ¯
    0.26
     goal
    0.24
    å°±æĺ¯
    0.24
    Activations Density 0.216%

    No Known Activations