© 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. 11860
    Prev
    Next
    INDEX
    Explanations

    talked with / asked to

    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
     inertia
    -0.20
    cock
    -0.19
    /tests
    -0.19
    bote
    -0.19
     quarters
    -0.18
    anic
    -0.18
    Quarter
    -0.18
    idal
    -0.18
    éģij
    -0.18
     oneself
    -0.17
    POSITIVE LOGITS
    以ä¸ĭåĩłä¸ª
    0.24
    ä¸Ģè¡Į
    0.24
    è§ģè¯ģäºĨ
    0.22
    å¾ĹåĪ°äºĨ
    0.21
    ä¸ĭéĿ¢æĺ¯
    0.21
    ä¸ĭéĿ¢å°±
    0.21
    æĹ¶è¡¨ç¤º
    0.21
    å°±æѤ
    0.20
    æѤåĪ»
    0.19
    åĪ¶å®ļäºĨ
    0.19
    Activations Density 0.030%

    No Known Activations