© 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. 16430
    Prev
    Next
    INDEX
    Explanations

    role of

    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
    WISE
    -0.21
    atform
    -0.19
    èģĮä¸ļçĶŁæ¶¯
    -0.19
    è§IJ
    -0.18
    并ä¸İ
    -0.18
     erotisk
    -0.18
    篦
    -0.18
     situations
    -0.18
     nao
    -0.17
    reta
    -0.17
    POSITIVE LOGITS
    äººåľ¨
    0.25
    è§Ĵèī²
    0.21
     role
    0.21
     Role
    0.20
     ROLE
    0.19
     rôle
    0.19
    ulos
    0.19
     technology
    0.19
    -playing
    0.19
    à¹Ģหล
    0.19
    Activations Density 0.172%

    No Known Activations