© 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. 14075
    Prev
    Next
    INDEX
    Explanations

    alarm

    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
    æ·«
    -0.23
    aju
    -0.19
    bol
    -0.19
    bolt
    -0.19
    èĻİ
    -0.19
    交æĺĵå¹³åı°
    -0.18
     lion
    -0.18
    rame
    -0.18
    ä¾ĥ
    -0.18
    å·´åŁº
    -0.18
    POSITIVE LOGITS
    æĹ¥è®¯
    0.21
    -machine
    0.20
    没å¿ħè¦ģ
    0.19
    åĪ°æŶåĢĻ
    0.19
    èµ·åºĬ
    0.19
    éĹ¹
    0.19
     иÑģпол
    0.19
    виÑĤ
    0.19
     wake
    0.18
    çĶµè¯Ŀ
    0.18
    Activations Density 0.011%

    No Known Activations