© 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. 16626
    Prev
    Next
    INDEX
    Explanations

    amniotic

    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
    çĩĥ
    -0.20
     Tutorial
    -0.19
    ä¸Ń级
    -0.18
    avid
    -0.18
     roma
    -0.18
     Trev
    -0.18
    FFE
    -0.18
    åį«
    -0.18
    æĢĨ
    -0.17
     retry
    -0.17
    POSITIVE LOGITS
     pudd
    0.24
    jis
    0.19
    é£İåij³
    0.19
    emes
    0.18
    æĤĦæĤĦ
    0.18
    è½²
    0.18
    ACTIVE
    0.17
    ctors
    0.17
     sieve
    0.17
     progressives
    0.17
    Activations Density 0.011%

    No Known Activations