© 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. 15084
    Prev
    Next
    INDEX
    Explanations

    you are here

    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
    éĹ®ä»ĸ
    -0.24
    æķ¬
    -0.22
     tight
    -0.20
    æĺİæĻ°
    -0.20
    ç§ģ
    -0.20
    裹
    -0.19
    宣
    -0.19
    adt
    -0.19
    èѦåijĬ
    -0.18
    以èī²
    -0.18
    POSITIVE LOGITS
     okreÅĽlon
    0.19
    _PROFILE
    0.19
    returnValue
    0.17
    ä¸Ģä¼ļåĦ¿
    0.17
    羣æĺ¯
    0.17
    ä¼ģä¸ļçļĦ
    0.17
    è¿Ļéĥ¨åĪĨ
    0.17
    åħ·ä½ĵçļĦ
    0.17
     Decom
    0.17
    ENTA
    0.17
    Activations Density 0.005%

    No Known Activations