© 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. 15630
    Prev
    Next
    INDEX
    Explanations

    "believe" or "disbelief"

    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
    达人
    -0.20
    ä¸į妨
    -0.19
    ä¸įå®ļ
    -0.19
    æŨ
    -0.18
    ök
    -0.18
    è¶ĭåIJij
    -0.17
    heimer
    -0.17
    åij£
    -0.17
    èIJ¥åķĨ
    -0.17
     Brend
    -0.17
    POSITIVE LOGITS
    rides
    0.21
    没æĥ³åĪ°
    0.20
    ingly
    0.19
    åĻľ
    0.18
    æĺ¯çľŁçļĦ
    0.18
    åį´åıĪ
    0.18
    acs
    0.18
    gro
    0.18
    imulation
    0.17
    ãģĵãģ¨ãģ«
    0.17
    Activations Density 0.007%

    No Known Activations