© 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. 15842
    Prev
    Next
    INDEX
    Explanations

    astronomical designations

    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
    嵯
    -0.22
    ridged
    -0.21
    ereg
    -0.21
    hic
    -0.20
    èĵ¼
    -0.20
    ÙĬØŃ
    -0.19
    ÑĢег
    -0.19
    iral
    -0.19
    å¸ĤæĶ¿
    -0.19
    vided
    -0.19
    POSITIVE LOGITS
    åѤç«ĭ
    0.25
    åı·
    0.22
    åѤ
    0.20
    éĻĦè¿ij
    0.19
    addr
    0.19
    1
    0.19
    éĤ»å±ħ
    0.19
     unidentified
    0.18
     isolate
    0.18
    ç²Ĺ
    0.18
    Activations Density 0.077%

    No Known Activations