© 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. 14397
    Prev
    Next
    INDEX
    Explanations

    names of creators or directors

    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
    åĭĥ
    -0.20
    -fly
    -0.20
    佯
    -0.20
    çIJĥè¿·
    -0.19
    çİīçŁ³
    -0.19
    æīįåıijçİ°
    -0.18
    -food
    -0.18
    俾
    -0.18
    YNC
    -0.18
    éĺµéĺµ
    -0.18
    POSITIVE LOGITS
    ä¸ĸçķĮè§Ĥ
    0.23
    å·¥ä½ľå®¤
    0.23
    åĩºåĵģ
    0.23
    è§ĦåĪĴ
    0.22
    设计
    0.22
    AndView
    0.22
    亲èĩª
    0.21
     ÐIJлекÑģан
    0.20
    ç¼ĸåī§
    0.19
    reator
    0.19
    Activations Density 0.049%

    No Known Activations