© 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. 11079
    Prev
    Next
    INDEX
    Explanations

    sentiment and confidence

    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
    sol
    -0.19
    Interested
    -0.19
    第ä¸īèĢħ
    -0.19
    nf
    -0.19
    InBackground
    -0.18
    åıijçİ°éĹ®é¢ĺ
    -0.18
    æĦıæĥ³ä¸įåĪ°
    -0.18
    stück
    -0.17
    æĥ³æī¾
    -0.17
    è§Ħ模åĮĸ
    -0.17
    POSITIVE LOGITS
    ä¿¡å¿ĥ
    0.33
    æľªæĿ¥çļĦ
    0.24
    æľīä¿¡å¿ĥ
    0.23
    çļĦä¿¡å¿ĥ
    0.23
    æĤ²è§Ĥ
    0.22
    ä¹IJè§Ĥ
    0.22
    æľªæĿ¥
    0.22
    å¯¹æľªæĿ¥
    0.21
    å±ķæľĽ
    0.21
    åħ¨çIJĥç»ıæµİ
    0.21
    Activations Density 0.019%

    No Known Activations