© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48029
    Prev
    Next
    INDEX
    Explanations

    existential questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĭĩäºİåĪĽæĸ°
    -0.07
    á»ķ
    -0.07
    æ´»è·ĥçļĦ
    -0.06
    beau
    -0.06
     characteristic
    -0.06
    able
    -0.06
    icha
    -0.06
    forte
    -0.06
     khas
    -0.06
    öhn
    -0.06
    POSITIVE LOGITS
    èĦĨå¼±
    0.10
    çľĭéĢı
    0.10
    认è¯ĨåĪ°
    0.09
    æĦıè¯ĨåĪ°
    0.08
    ä¸ĢåĪĩéĥ½æĺ¯
    0.08
    .bb
    0.08
    ç»Īæŀģ
    0.08
    æŁ¥çľĭæīĢæľī
    0.08
    渺å°ı
    0.08
    转çŀ¬
    0.08
    Activations Density 0.090%

    No Known Activations