© 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. 13274
    Prev
    Next
    INDEX
    Explanations

    codes and identifiers

    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
    ror
    -0.20
    åIJĦè¡Į
    -0.19
    è¡ħ
    -0.19
    igy
    -0.18
    ä¸ĵåľº
    -0.18
    opsis
    -0.18
     unsus
    -0.18
    onus
    -0.18
    zier
    -0.17
    etu
    -0.17
    POSITIVE LOGITS
    大家ä¸Ģèµ·
    0.18
    (IP
    0.18
     ìĹŃ
    0.18
    榻
    0.18
    GP
    0.17
    à¸Ħà¸Ńย
    0.17
    æĸĻ
    0.17
    岸边
    0.17
     Reese
    0.17
    apel
    0.17
    Activations Density 0.014%

    No Known Activations