© 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. 15545
    Prev
    Next
    INDEX
    Explanations

    at your option

    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
     Ub
    -0.22
    éĩįç»Ħ
    -0.21
    éĺŁä¼į
    -0.20
    å¿ħ
    -0.20
    Ub
    -0.20
    undy
    -0.19
    ween
    -0.19
    åIJĪçIJĨ
    -0.19
    èĹı
    -0.19
    çļĦåħ·ä½ĵ
    -0.19
    POSITIVE LOGITS
    çķª
    0.21
    ¾ç¤º
    0.20
    (push
    0.20
    èĩªè´Ł
    0.19
    onto
    0.19
    iotic
    0.19
    INLINE
    0.19
    åĿĢ
    0.19
    糧
    0.19
    è¤
    0.19
    Activations Density 0.002%

    No Known Activations