© 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. 13548
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è¿Ļå¼ł
    -0.20
    æŁĦ
    -0.20
    è´±
    -0.20
    à¸ģระà¸Ĺ
    -0.19
    .shadow
    -0.19
    omen
    -0.19
    atism
    -0.19
     оÑĤзÑĭв
    -0.18
     оÑĤз
    -0.18
    èĥĮ
    -0.18
    POSITIVE LOGITS
    ulia
    0.22
    ocos
    0.21
    expert
    0.20
    ä¸ļä½Ļ
    0.20
    andas
    0.20
    秣
    0.20
    çģ¯
    0.19
    ç¼Ĵ
    0.18
    èĸ¤
    0.18
    è¾ħåĬ©
    0.18
    Activations Density 0.000%

    No Known Activations