© 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. 29227
    Prev
    Next
    INDEX
    Explanations

    `Font Awesome 5 Free`

    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
    ihe
    -0.09
    ILLE
    -0.08
    ãģĭãģĴ
    -0.07
    龸çİĭ
    -0.07
    sto
    -0.07
    ³
    -0.07
    ROADCAST
    -0.07
    /download
    -0.07
    ossa
    -0.07
    ouch
    -0.07
    POSITIVE LOGITS
    æĶ¯
    0.08
    vel
    0.08
    åħ¶å®ĥåªĴä½ĵ
    0.07
     appunto
    0.06
    VEL
    0.06
    ä½ĨæĦ¿
    0.06
    ắc
    0.06
    uelle
    0.06
    Ap
    0.06
    ä»°
    0.06
    Activations Density 0.002%

    No Known Activations