© 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. 15464
    Prev
    Next
    INDEX
    Explanations

    filtering and selection

    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
    åľ©
    -0.19
     Vaults
    -0.18
    ä¼
    -0.18
    æ¹ĺ
    -0.18
    nesc
    -0.18
    .forName
    -0.18
    _ROUT
    -0.18
    .translate
    -0.18
    æľĢç¾İ
    -0.17
    /current
    -0.17
    POSITIVE LOGITS
    çŃĽéĢī
    0.27
    æ·ĺæ±°
    0.22
     FILTER
    0.21
    è¿ĩ滤
    0.21
     filters
    0.20
    FILTER
    0.20
     ÑĥÑģл
    0.20
    бÑĥд
    0.20
    mun
    0.20
    åĪ°æľĢåIJİ
    0.20
    Activations Density 0.085%

    No Known Activations