© 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. 16195
    Prev
    Next
    INDEX
    Explanations

    state changes

    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
     gro
    -0.22
    ÑĤай
    -0.19
    MAS
    -0.19
    è¿ĩçļĦ
    -0.19
     sup
    -0.18
    iedo
    -0.18
    ä¸Ģä¸ĸ
    -0.17
    /shared
    -0.17
    exp
    -0.17
    ortal
    -0.17
    POSITIVE LOGITS
    åıĺ为
    0.27
    åıĺæĪIJ
    0.26
    åıĺå¾ĹæĽ´åĬł
    0.25
    åıĺæĪIJäºĨ
    0.25
    åıĺå¾Ĺ
    0.25
    æĪIJ为
    0.24
    éĢIJæ¸IJ
    0.24
     becomes
    0.24
    ç´§ç´§åĽ´ç»ķ
    0.24
     dần
    0.24
    Activations Density 0.054%

    No Known Activations