© 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. 43993
    Prev
    Next
    INDEX
    Explanations

    direction: left, right, backward, side

    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
     teng
    -0.08
    踪
    -0.07
    inkt
    -0.07
    为æĪijåĽ½
    -0.06
    大åħ³
    -0.06
    çĸĻçĺ©
    -0.06
    äºĮ代
    -0.06
    åľ¨ä¼Ĺå¤ļ
    -0.06
    ä¸Ģä½ľ
    -0.06
    uksi
    -0.06
    POSITIVE LOGITS
    /left
    0.09
    å¾Ģ
    0.08
    ToLeft
    0.08
    /back
    0.08
    :left
    0.08
    _sym
    0.08
    _backward
    0.08
    å¾ĢéĩĮ
    0.07
    rown
    0.07
    .LEFT
    0.07
    Activations Density 0.004%

    No Known Activations