© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 8179
    Prev
    Next
    INDEX
    Explanations

    examples, questions, and code

    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
    å¦Ĥçģ«
    -0.08
    **”
    -0.07
    \)
    -0.07
     ãĢģ
    -0.07
     blah
    -0.07
    (?)
    -0.07
    å½ĵçĦ¶
    -0.07
    *”
    -0.07
    缸åºĶ
    -0.06
    è¦ģä¹Ī
    -0.06
    POSITIVE LOGITS
    _:
    0.10
    "":
    0.10
    ':
    0.10
    å°±çŁ¥éģĵäºĨ
    0.10
     ():
    0.09
    ']:
    0.09
     {}:
    0.09
    __:
    0.09
    '):
    0.09
    ":
    0.09
    Activations Density 0.016%

    No Known Activations