© 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. 15351
    Prev
    Next
    INDEX
    Explanations

    age ranges

    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
    ikan
    -0.20
    棼
    -0.19
    åĨħå¹ķ
    -0.19
    æĪĸå¤ļ
    -0.19
     alto
    -0.19
    æİĴåIJį第ä¸Ģ
    -0.18
    æľĢå¤ļçļĦ
    -0.18
    禽
    -0.17
    levation
    -0.17
     bailout
    -0.17
    POSITIVE LOGITS
    è±ģ
    0.23
    ecz
    0.20
     Exceptions
    0.18
    ãĥŃãĥ³
    0.18
    èĩ³
    0.18
    оÑĤов
    0.18
    -ID
    0.18
    _subject
    0.18
    ä½ĵåĬĽ
    0.18
     hollow
    0.18
    Activations Density 0.035%

    No Known Activations