© 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. 21206
    Prev
    Next
    INDEX
    Explanations

    code delimiters and punctuation

    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
    容
    -0.07
    åıijèµ·
    -0.07
    è¾
    -0.07
     неком
    -0.07
    天ç±ģ
    -0.07
     Ùħرت
    -0.07
    å¤ĸæĿ¥
    -0.06
    tie
    -0.06
    åįģ大
    -0.06
    å¦Ĥçİī
    -0.06
    POSITIVE LOGITS
    以西
    0.08
    èĩªå·²
    0.08
    unch
    0.07
    emoji
    0.07
    VAR
    0.07
    çĸ¤
    0.07
    åĽ½å®ī
    0.07
    uis
    0.06
    ÑĢоз
    0.06
    æļ´åĪ©
    0.06
    Activations Density 0.009%

    No Known Activations