© 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. 14935
    Prev
    Next
    INDEX
    Explanations

    local locations and records

    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
    ystone
    -0.07
    ynt
    -0.07
    attel
    -0.07
    åľ¨ä¿Ŀè¯ģ
    -0.07
    Compression
    -0.06
    pital
    -0.06
    ynet
    -0.06
    ATTLE
    -0.06
    å°½éĩıåĩıå°ij
    -0.06
    fighters
    -0.06
    POSITIVE LOGITS
    æ¬Ħ
    0.08
    å·¡
    0.08
    äºİäºĭ
    0.07
    åħ¶éģĵ
    0.07
    æĮĤåľ¨
    0.07
    åĨĻåľ¨
    0.07
    年建
    0.07
    èĢ¦
    0.07
    LOC
    0.07
    天ä¸ĭ
    0.07
    Activations Density 1.297%

    No Known Activations