© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15378
    Prev
    Next
    INDEX
    Explanations

    granite

    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
    ings
    -0.20
    ened
    -0.20
    wagon
    -0.19
    ening
    -0.18
    möglich
    -0.18
    endar
    -0.17
    èĬ
    -0.17
    æĦī
    -0.17
    liness
    -0.17
    _SOCKET
    -0.16
    POSITIVE LOGITS
    ../
    0.22
    ville
    0.21
    forth
    0.18
     Ñģвоими
    0.17
    eq
    0.17
    å±±èĦī
    0.16
    åIJĮèĥŀ
    0.16
    鼷éľĨ
    0.16
    à¹ģà¸Ķà¸ĩ
    0.16
    å±±åºĦ
    0.16
    Activations Density 0.002%

    No Known Activations