© 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. 14157
    Prev
    Next
    INDEX
    Explanations

    just shy of

    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
     Ñģли
    -0.21
    åĪĿ
    -0.20
    æ¸ħæī«
    -0.20
    åı°
    -0.19
    好ä¸į容æĺĵ
    -0.19
    æĹ¥èµ·
    -0.18
    éĿ¢ç§¯çº¦
    -0.18
    å¹´èµ·
    -0.18
    岫
    -0.18
    FD
    -0.18
    POSITIVE LOGITS
    ret
    0.23
    oras
    0.21
    èĢĮå·²
    0.19
    å°±èĥ½
    0.19
    rett
    0.19
    éĢĢä¼ij
    0.19
    å®Įç¾İ
    0.19
    alen
    0.19
    .ret
    0.19
     fullName
    0.18
    Activations Density 0.028%

    No Known Activations