© 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. 10870
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

    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
    licht
    -0.25
     Cla
    -0.23
    agram
    -0.22
    olg
    -0.21
    achs
    -0.20
    ROTO
    -0.20
    chet
    -0.19
    è¶ħæłĩ
    -0.19
    ichten
    -0.19
    åĬłéĢŁ
    -0.19
    POSITIVE LOGITS
    æ¶Ī
    0.20
    addons
    0.20
    为åĩĨ
    0.20
    ÑĢид
    0.19
    çľ¼è§Ĵ
    0.19
    å»ĵ
    0.19
    æµĭéĩı
    0.19
    íķij
    0.19
    ä¸įä¸ĭ
    0.19
    å¦ĩ女
    0.19
    Activations Density 0.043%

    No Known Activations