© 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. 15852
    Prev
    Next
    INDEX
    Explanations

    polymerization

    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
    ctype
    -0.18
     gái
    -0.17
    ÑĤал
    -0.16
    sse
    -0.16
    ses
    -0.15
    ıģ
    -0.15
    sel
    -0.15
    _FOREACH
    -0.15
    èĢģ人
    -0.15
    elmet
    -0.15
    POSITIVE LOGITS
    ically
    0.21
    ized
    0.19
    ization
    0.19
    izable
    0.18
    ity
    0.18
    ics
    0.17
    ikhail
    0.16
    oot
    0.16
    趱
    0.16
    à¹Į
    0.16
    Activations Density 0.046%

    No Known Activations