© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 456
    Prev
    Next
    INDEX
    Explanations

    URLs or links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    带åĽŀ
    -0.28
    è¿ĻäºĽéĹ®é¢ĺ
    -0.24
    å¦Ĵ
    -0.23
    è¿Ļå¥Ĺ
    -0.23
    è¿ĻäºĽä¸ľè¥¿
    -0.23
    åħįè´£
    -0.22
    è¿Ļ家ä¼Ļ
    -0.22
    ÑģÑĥÑĤ
    -0.21
    urge
    -0.21
    è¿Ļ份
    -0.21
    POSITIVE LOGITS
    link
    0.30
     link
    0.28
    å²Ķ
    0.26
     links
    0.26
    ãĥªãĥ³ãĤ¯
    0.24
     LINK
    0.24
    éĵ¾æİ¥
    0.24
     Verb
    0.24
    links
    0.24
    弯
    0.23
    Activations Density 0.022%

    No Known Activations