© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14983
    Prev
    Next
    INDEX
    Explanations

    necessary conditions, permits, space, directions, skills

    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
    ä¸ĢåĪĨéĴŁ
    -0.20
    agal
    -0.19
    ä¸Ģ个éĹ®é¢ĺ
    -0.19
    æģĭæĥħ
    -0.19
    éĽĨè£ħ
    -0.18
    人æ°ijæľįåĬ¡
    -0.18
    ality
    -0.18
    licit
    -0.17
    æīĢæıIJä¾ĽçļĦ
    -0.17
    spender
    -0.17
    POSITIVE LOGITS
     necessary
    0.29
    å¿ħè¦ģçļĦ
    0.27
    æīĭç»Ń
    0.25
    åºĶæľīçļĦ
    0.25
     needed
    0.24
     required
    0.24
    æĬĢæľ¯åĴĮ
    0.24
    éħįå¥Ĺ
    0.23
    å¿ħè¦ģ
    0.23
    necessary
    0.22
    Activations Density 0.028%

    No Known Activations