© 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. 38301
    Prev
    Next
    INDEX
    Explanations

    python code blocks

    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
    æĹıèĩªæ²»åİ¿
    -0.07
    SSI
    -0.07
    वार
    -0.07
    çŃīä¸ļåĬ¡
    -0.07
    è®®äºĭ
    -0.07
    å°Ķçī¹
    -0.07
    inheritDoc
    -0.07
     giunta
    -0.07
    pires
    -0.07
    以轻
    -0.07
    POSITIVE LOGITS
    æĸŃ
    0.08
    åĨį
    0.07
    _=
    0.07
    åıĸåħ¶
    0.07
    åīªåĪĢ
    0.07
    agem
    0.06
    å½¢
    0.06
    åħ¶ä¸Ńæľī
    0.06
    >".
    0.06
    åħ¶ä¸ŃçļĦ
    0.06
    Activations Density 0.306%

    No Known Activations