© 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. 45000
    Prev
    Next
    INDEX
    Explanations

    DEFINITION, PROJECT, Romero, adult

    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
    afil
    -0.07
    ÙĦس
    -0.07
    å¸ľ
    -0.07
    atera
    -0.07
    ä¹Ŀä¹Ŀ
    -0.07
     bomb
    -0.06
     cig
    -0.06
    aters
    -0.06
    Bomb
    -0.06
     Bomb
    -0.06
    POSITIVE LOGITS
    æĺĵ
    0.08
     Kee
    0.07
    èIJĮèĬ½
    0.07
    çĶ°
    0.07
    æľºæ¢°
    0.07
    æŀ¶æŀĦ
    0.07
     mechanically
    0.06
    revet
    0.06
    yyy
    0.06
    rench
    0.06
    Activations Density 0.086%

    No Known Activations