© 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. 13898
    Prev
    Next
    INDEX
    Explanations

    XS

    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
    éģĵåħ·
    -0.22
    è®·
    -0.18
    _Account
    -0.18
    овиÑĩ
    -0.18
    ined
    -0.18
    åĬ²
    -0.18
    kar
    -0.17
    \:
    -0.17
    _fk
    -0.17
    Apps
    -0.17
    POSITIVE LOGITS
    æĿ¯
    0.21
    è´£ç¼ĸ
    0.19
     Toy
    0.18
    å®ĵ
    0.18
    али
    0.18
    ä¸įæĸŃ
    0.17
    uese
    0.17
    ose
    0.17
    onso
    0.17
    PEC
    0.16
    Activations Density 0.179%

    No Known Activations