© 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. 33781
    Prev
    Next
    INDEX
    Explanations

    structural strength and components

    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
    æµĵåİļ
    -0.08
    ละ
    -0.07
     Etiqu
    -0.07
    æ°Ľ
    -0.07
     flav
    -0.07
    ç´Ľ
    -0.07
     íĻķìĤ°
    -0.07
    æ¿ĥåİļ
    -0.07
    è¿·éĽ¾
    -0.06
    vos
    -0.06
    POSITIVE LOGITS
    åıĹåĬĽ
    0.14
     strength
    0.14
    æī¿åıĹ
    0.14
    æī¿éĩį
    0.14
    èĥ½æī¿åıĹ
    0.13
    æī¿åıĹçļĦ
    0.12
    strength
    0.12
     Strength
    0.12
    åºĶåĬĽ
    0.11
    çŃĭ
    0.11
    Activations Density 0.242%

    No Known Activations