© 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. 13053
    Prev
    Next
    INDEX
    Explanations

    stopping or restricting access

    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
    åĶ³
    -0.20
    裸
    -0.20
    ule
    -0.20
    é¢Ĩçķ¥
    -0.18
    peek
    -0.18
    åIJ»
    -0.18
    apo
    -0.18
     поÑĤеÑĢ
    -0.18
    assy
    -0.18
    翱
    -0.18
    POSITIVE LOGITS
    ä¸į让
    0.36
    éĺ²æŃ¢
    0.26
    å°ģéĹŃ
    0.25
    åłµå¡ŀ
    0.24
    åłµ
    0.23
    å°ģéĶģ
    0.22
    åĽ´
    0.22
    便äºİ
    0.22
    æĮ¡
    0.21
    åĮħåĽ´
    0.21
    Activations Density 0.016%

    No Known Activations