© 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. 13946
    Prev
    Next
    INDEX
    Explanations

    basic namevaluepair

    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
    nid
    -0.20
    elen
    -0.20
    lags
    -0.20
    rel
    -0.19
    olum
    -0.19
    relationships
    -0.19
    é³ŀ
    -0.19
    dn
    -0.18
    å¡
    -0.18
    lama
    -0.18
    POSITIVE LOGITS
    æľºåĬ¨
    0.23
    çĺ«
    0.22
    åħ¬çĶ¨
    0.22
    ä¸Ģæŀļ
    0.21
    è®®äºĭ
    0.20
    _native
    0.20
    çºłéĶĻ
    0.20
    ä¸Ģå¥Ĺ
    0.20
    æ¯ıä¸Ģ次
    0.19
    è¿Ļå¥Ĺ
    0.19
    Activations Density 0.014%

    No Known Activations