© 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. 12297
    Prev
    Next
    INDEX
    Explanations

    Cambridge

    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
    teenth
    -0.20
    ter
    -0.20
    swith
    -0.19
    thon
    -0.18
    nt
    -0.17
    the
    -0.17
    lijke
    -0.17
    ä¸ĵ人
    -0.17
    nej
    -0.17
    wards
    -0.17
    POSITIVE LOGITS
    ãĥ³ãĤ°
    0.21
    ium
    0.17
    ä½Ĩä¸įéĻIJäºİ
    0.16
    IAN
    0.15
    maid
    0.15
    ä¿Ł
    0.14
    learner
    0.14
    -era
    0.14
     minded
    0.14
     Gregg
    0.14
    Activations Density 0.004%

    No Known Activations