© 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. 13936
    Prev
    Next
    INDEX
    Explanations

    best possible

    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
    ernes
    -0.20
    mere
    -0.20
    ży
    -0.19
    æĹ¥åŃIJ
    -0.19
    tó
    -0.18
    ç»ĵæĿŁäºĨ
    -0.18
    StateChanged
    -0.18
    afil
    -0.18
    åĩºæĿ¥äºĨ
    -0.18
    èIJ½åĪ°å®ŀ
    -0.18
    POSITIVE LOGITS
     best
    0.24
    å°½åı¯èĥ½
    0.22
    俱
    0.22
     possible
    0.22
    ering
    0.21
     faire
    0.21
    å°½åĬĽ
    0.20
    æľĢéĢĤåIJĪ
    0.20
    åĵģè´¨
    0.20
     amounts
    0.20
    Activations Density 0.036%

    No Known Activations