© 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. 12322
    Prev
    Next
    INDEX
    Explanations

    want to

    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
    ä½łåĸľæ¬¢
    -0.25
    çĪ±ä½ł
    -0.23
     enough
    -0.22
    ä»Ģä¹Īä¸ľè¥¿
    -0.21
    å°Ĩèĩªå·±çļĦ
    -0.21
     Äijủ
    -0.20
    asti
    -0.20
    彤
    -0.20
    ä½łæĥ³
    -0.20
    ableView
    -0.19
    POSITIVE LOGITS
     latter
    0.22
    éĢģåĪ°
    0.21
    带åĪ°
    0.20
    yles
    0.19
    PLATFORM
    0.19
    éĢģå¾Ģ
    0.18
    SPATH
    0.18
    .sym
    0.18
    urar
    0.18
    ç»ĦæĪIJçļĦ
    0.18
    Activations Density 0.040%

    No Known Activations