© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    transformation and conversion

    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
    OMA
    -0.08
    交æ±ĩå¤Ħ
    -0.07
    olla
    -0.07
    _helpers
    -0.07
    æł¹æį®åħ¶
    -0.07
    ojis
    -0.07
    çĶ±äºİåħ¶
    -0.07
    éļ¨æĻĤ
    -0.07
    วย
    -0.07
    éļ
    -0.07
    POSITIVE LOGITS
    转åĮĸ
    0.09
     conversion
    0.09
     transformation
    0.08
     conversions
    0.08
     converting
    0.07
    æį¢
    0.07
    Transformation
    0.07
    ä¸įæ¶īåıĬ
    0.07
    conversion
    0.07
     essentially
    0.07
    Activations Density 0.022%

    No Known Activations