© 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. 13422
    Prev
    Next
    INDEX
    Explanations

    log, dB, magnitude

    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
    ä¹ĭæĥħ
    -0.22
     Ratio
    -0.21
    å¾Ĺèµ·
    -0.21
    åįł
    -0.20
    éĥİ
    -0.20
    æ¯Ķä¾ĭ
    -0.20
    REQUIRED
    -0.19
    æľīæľŁ
    -0.19
    	TR
    -0.19
    atron
    -0.19
    POSITIVE LOGITS
    =log
    0.24
    å¯Ĵ
    0.21
    èij¶
    0.20
    å¯ĵ
    0.20
    寡
    0.19
    éĵħ
    0.19
    åįģåĩłå¹´
    0.18
     Conte
    0.18
    nist
    0.18
    .Tool
    0.18
    Activations Density 0.260%

    No Known Activations