© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42244
    Prev
    Next
    INDEX
    Explanations

    encoding reference 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
    ocas
    -0.07
    ear
    -0.06
     ICollection
    -0.06
    engo
    -0.06
    æľĢéľĢè¦ģ
    -0.06
    æĸŃäºĨ
    -0.06
    åıªçĶ¨
    -0.06
    anka
    -0.06
    uela
    -0.06
    äºİä¸Ģ
    -0.06
    POSITIVE LOGITS
    /***/
    0.08
     chiff
    0.08
    unku
    0.08
    ä¸įèĩªç¦ģ
    0.08
     unprotected
    0.08
    iagnostics
    0.08
    anmar
    0.07
    erima
    0.07
    atering
    0.07
    icontrol
    0.07
    Activations Density 0.025%

    No Known Activations