© 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. 31360
    Prev
    Next
    INDEX
    Explanations

    escaping characters

    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
     sourceMapping
    -0.07
    èĥ½æī¾åĪ°
    -0.07
    åį´åıijçİ°
    -0.07
    ero
    -0.06
    Assignable
    -0.06
    çŃĶ
    -0.06
     addiction
    -0.06
    åı¦æľī
    -0.06
    ä¸įéĹ®
    -0.06
     compares
    -0.06
    POSITIVE LOGITS
    VEL
    0.10
     consciously
    0.08
     literal
    0.08
    avy
    0.08
    ASCII
    0.08
     Unicode
    0.07
    æľĿéĺ³
    0.07
    å®ŀéĻħæݧåĪ¶
    0.07
    åį°åĪ·
    0.07
     syntax
    0.07
    Activations Density 0.037%

    No Known Activations