© 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. 19371
    Prev
    Next
    INDEX
    Explanations

    `label` followed by `">` or `pen` followed by `(s`

    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
    åıijæ¶Īæģ¯
    -0.08
    _OPER
    -0.07
    ELY
    -0.07
    齡
    -0.07
    enheim
    -0.07
    Earn
    -0.07
    менов
    -0.07
    à¤Ĺत
    -0.07
    ยำ
    -0.07
    rtl
    -0.07
    POSITIVE LOGITS
    specified
    0.08
     fest
    0.08
    设å®ļçļĦ
    0.07
    .DEFAULT
    0.07
    sons
    0.07
     specified
    0.07
    è³ĩ
    0.07
    .getDefault
    0.07
    åħ¹
    0.07
    è§Ħå®ļçļĦ
    0.07
    Activations Density 0.060%

    No Known Activations