© 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. 13003
    Prev
    Next
    INDEX
    Explanations

    House, Senate, Congress, Parliament

    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
    CERT
    -0.24
    é¢Ĩè·ij
    -0.21
    çŃ¾çº¦
    -0.20
    欧ç¾İ
    -0.20
     vic
    -0.20
    åħ¬çĽĬ
    -0.19
    æĢ»åħ¬åı¸
    -0.19
    çĶ°åĽŃ
    -0.19
    etail
    -0.19
    çīµå¼ķ
    -0.19
    POSITIVE LOGITS
    常å§Ķä¼ļ
    0.31
    审议
    0.28
    è®®äºĭ
    0.28
     recess
    0.28
    è®®åijĺ
    0.27
    座ä½į
    0.27
    å¸Ń
    0.26
     phiên
    0.24
    å§Ķåijĺ
    0.24
    æ¡Į
    0.24
    Activations Density 0.094%

    No Known Activations