© 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. 2259
    Prev
    Next
    INDEX
    Explanations

    top, bottom, last, head, tail

    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
    anza
    -0.10
    ubes
    -0.08
    onato
    -0.07
    iaux
    -0.07
    _PHASE
    -0.07
    atoire
    -0.07
    BoxLayout
    -0.07
    ziem
    -0.07
    çĶ·åĦ¿
    -0.07
    fam
    -0.07
    POSITIVE LOGITS
    ä¸įæĸŃ
    0.09
    å½ĵåīį
    0.08
    éĵ¾
    0.08
    å½ĵåīįçļĦ
    0.08
    most
    0.08
    å±Ĥ
    0.07
    å±ĤçļĦ
    0.07
    ä¸įæĸŃæĽ´æĸ°
    0.07
    æĺĵ
    0.07
    ä¸įæĸŃçļĦ
    0.07
    Activations Density 0.033%

    No Known Activations