© 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. 13710
    Prev
    Next
    INDEX
    Explanations

    tilde symbol

    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
    chine
    -0.09
    iggio
    -0.08
    ills
    -0.08
    regel
    -0.08
    furt
    -0.07
    isto
    -0.07
    innacle
    -0.07
    è°ģ家
    -0.07
    å°½åħ¶
    -0.06
    تÙħاد
    -0.06
    POSITIVE LOGITS
    /original
    0.08
    akedown
    0.08
    ature
    0.08
    agger
    0.08
    ำ
    0.08
    /false
    0.07
     обÑĢазом
    0.07
    ìļ±
    0.07
    Separated
    0.07
    çĪĨ
    0.07
    Activations Density 0.005%

    No Known Activations