© 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. 13559
    Prev
    Next
    INDEX
    Explanations

    mysteries/novels

    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
    affles
    -0.21
    çĶŁæľº
    -0.21
    åıŃ
    -0.21
    åľ¨çݩ家ä¸Ń
    -0.20
    DECL
    -0.19
    .sap
    -0.18
    æ·±æ·±åľ°
    -0.18
    ToWorld
    -0.18
    еÑģÑĤи
    -0.18
    -example
    -0.17
    POSITIVE LOGITS
    æ¯ı次
    0.22
    侦
    0.22
    atable
    0.22
    å°ı说
    0.21
     detective
    0.21
    éĢĢä¼ij
    0.21
    侦æİ¢
    0.20
    æħ¶
    0.20
    ä¾¦æŁ¥
    0.20
    ç³»åĪĹ
    0.20
    Activations Density 0.033%

    No Known Activations