© 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. 14696
    Prev
    Next
    INDEX
    Explanations

    assistant bots

    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
    ä¸ĢéĹ´
    -0.23
    ä¸į满
    -0.19
    bur
    -0.18
     requis
    -0.18
    æĸĽ
    -0.18
    Ãł
    -0.18
    .ipv
    -0.17
    lose
    -0.17
    ä¸įä¹ħ
    -0.17
    æŃ£è§Ħ
    -0.17
    POSITIVE LOGITS
    个æĢ§åĮĸ
    0.21
    管家
    0.21
    åijĺ
    0.20
    ä½ĵè´´
    0.20
     помоÑī
    0.20
    åħ¨å¤©
    0.19
    åIJĪä½ľåįıè®®
    0.19
    íķµ
    0.19
     голоÑģ
    0.18
    åĬ©æīĭ
    0.18
    Activations Density 0.021%

    No Known Activations