© 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. 16166
    Prev
    Next
    INDEX
    Explanations

    names followed by descriptive words

    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
    çĮ¾
    -0.08
    моÑĤ
    -0.06
    omot
    -0.06
    ä¸ŃåįĹ
    -0.06
    ieno
    -0.06
    iled
    -0.06
    quant
    -0.06
    roat
    -0.06
    åħ³
    -0.06
    Ñħ
    -0.06
    POSITIVE LOGITS
    TTg
    0.08
    είÏĤ
    0.08
     Belediyesi
    0.08
    anee
    0.07
    åłĤåłĤ
    0.07
    LICA
    0.07
     undermin
    0.07
    æķ°æį®çºłéĶĻ
    0.07
     setC
    0.07
    顾åIJįæĢĿ
    0.07
    Activations Density 0.181%

    No Known Activations