© 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. 11754
    Prev
    Next
    INDEX
    Explanations

    responsible for

    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¥Ħ
    -0.19
    æľºä¼ļ
    -0.18
    ivol
    -0.18
    åıĹæįŁ
    -0.18
    ripper
    -0.17
    æ°ijå¿ĥ
    -0.17
     sourceMapping
    -0.17
    odal
    -0.17
    åŁºæľ¬åİŁåĪĻ
    -0.17
    spir
    -0.17
    POSITIVE LOGITS
    ness
    0.24
    ity
    0.22
    è¿Ļä¸ĢåĪĩ
    0.20
    -looking
    0.19
    ities
    0.18
    EObject
    0.18
    heid
    0.18
    æĸ¼
    0.17
    äºİ
    0.17
    çļĦæĺ¯
    0.17
    Activations Density 0.014%

    No Known Activations