© 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. 16477
    Prev
    Next
    INDEX
    Explanations

    catch up

    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
    bai
    -0.18
    IFI
    -0.18
    aders
    -0.18
    ãģ¾ãģ¾
    -0.16
    æĻ°
    -0.16
    ç½Ĥ
    -0.16
    ä½ķå¤Ħ
    -0.16
    è¡¿
    -0.16
    .indices
    -0.16
    halb
    -0.16
    POSITIVE LOGITS
    lost
    0.20
     bicy
    0.19
    ingly
    0.19
    aper
    0.18
    svc
    0.17
    resp
    0.17
    wis
    0.17
    ØŃÙĪاÙĦ
    0.17
    æŶ髦
    0.17
     metic
    0.16
    Activations Density 0.004%

    No Known Activations