© 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. 3673
    Prev
    Next
    INDEX
    Explanations

    `

    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
    eke
    -0.07
    ¿
    -0.07
    unt
    -0.07
    å®ĥåĢij
    -0.07
    ike
    -0.07
    å¤ļä¸ĢäºĽ
    -0.07
    WK
    -0.07
    <|box_end|>
    -0.07
     Colony
    -0.07
    大åħ³
    -0.07
    POSITIVE LOGITS
    ksam
    0.06
    å¯¹æľ¬
    0.06
    athers
    0.06
     Constitutional
    0.06
    åĨ¶
    0.06
    lear
    0.06
     beur
    0.06
    eldon
    0.06
    iets
    0.06
    åĪ¤å®ļ
    0.06
    Activations Density 0.001%

    No Known Activations