© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14849
    Prev
    Next
    INDEX
    Explanations

    polite requests or instructions

    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
    erule
    -0.07
    anuts
    -0.07
    åĪĽæĸ°é©±åĬ¨
    -0.06
    åĩºåľŁ
    -0.06
    airo
    -0.06
    èĶ·
    -0.06
    ä¹į
    -0.06
    åı½
    -0.06
    icca
    -0.06
    itrine
    -0.06
    POSITIVE LOGITS
    ckill
    0.08
    cke
    0.07
    å¿ĥæĤ¦
    0.07
    åĨĻä¸Ĭ
    0.07
    èŀįåħ¥åĪ°
    0.07
    emb
    0.07
    åĨĻå®Į
    0.07
    jde
    0.07
    ycz
    0.07
    ullet
    0.06
    Activations Density 0.002%

    No Known Activations