© 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. 10914
    Prev
    Next
    INDEX
    Explanations

    header, Pragma, Attorney, Respondent

    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
    alus
    -0.21
    rans
    -0.20
    æīĭæ³ķ
    -0.19
    bö
    -0.19
    ensation
    -0.19
    (pe
    -0.19
    ipe
    -0.18
    atter
    -0.18
    è¯į
    -0.18
    Sky
    -0.17
    POSITIVE LOGITS
    ä¸īæĺ¯
    0.21
    åĽĽæĺ¯
    0.20
     Serg
    0.19
    åĶ·
    0.19
     Moy
    0.18
    è°©
    0.18
     nargin
    0.18
    åħ¬çĦ¶
    0.18
    æŃ¤äºº
    0.18
    è£Ļ
    0.18
    Activations Density 0.099%

    No Known Activations