© 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. 13149
    Prev
    Next
    INDEX
    Explanations

    your needs

    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
    .observe
    -0.20
     operating
    -0.19
    dbo
    -0.19
     expend
    -0.19
    lage
    -0.18
    计æıIJ
    -0.17
     dafür
    -0.17
    achts
    -0.17
    atin
    -0.17
    without
    -0.17
    POSITIVE LOGITS
    çIJIJ
    0.30
    éľĢè¦ģçĶ¨åĪ°
    0.30
    è¯īæ±Ĥ
    0.28
    éľĢæ±Ĥ
    0.28
    äºĭå®ľ
    0.27
     needs
    0.26
    åĶ®åIJİ
    0.25
    äºĭ项
    0.24
    éļ¾é¢ĺ
    0.24
    äºĭåĬ¡
    0.23
    Activations Density 0.044%

    No Known Activations