© 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. 41246
    Prev
    Next
    INDEX
    Explanations

    uncertainty or 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
    åİŁæľīçļĦ
    -0.08
    è¿ĩåİ»
    -0.07
    åįĵ
    -0.07
     simply
    -0.07
    vision
    -0.07
    符
    -0.07
    èī¯
    -0.06
    airo
    -0.06
     Ign
    -0.06
    åİŁæľī
    -0.06
    POSITIVE LOGITS
    ëł¹
    0.08
    Õµ
    0.08
    Õ½
    0.08
    è¿Ľä¸ĢæŃ¥æī©å¤§
    0.08
    æī¾æī¾
    0.07
    åħ¶å®ĥ
    0.07
    åĨįçľĭçľĭ
    0.07
    à¹Ħส
    0.07
    éĩįçĤ¹åĮºåŁŁ
    0.07
    kan
    0.07
    Activations Density 0.004%

    No Known Activations