© 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. 11634
    Prev
    Next
    INDEX
    Explanations

    granted permitted

    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
    å°±è¿Ļæł·
    -0.21
    arem
    -0.19
    erval
    -0.19
    tá
    -0.19
    æ¦
    -0.18
    HeaderValue
    -0.18
    åħ¶ä»ĸçļĦ
    -0.18
    èĭĶ
    -0.18
    MAND
    -0.17
    itsu
    -0.17
    POSITIVE LOGITS
    cdf
    0.20
     Mayer
    0.20
    åıĭè°Ĭ
    0.20
    æįĭ
    0.20
     Freund
    0.19
    beck
    0.19
    CDF
    0.18
     Huffington
    0.18
    å±
    0.17
     Boyle
    0.17
    Activations Density 0.002%

    No Known Activations