© 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. 33189
    Prev
    Next
    INDEX
    Explanations

    milk and honey

    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
    踵
    -0.08
    notated
    -0.08
    åĽ½å®¶è§Ħå®ļ
    -0.07
    å°Ĩåĩºçİ°
    -0.07
    éĥ½èĥ½å¤Ł
    -0.07
    ambo
    -0.07
    robe
    -0.07
    製
    -0.07
    ugal
    -0.07
    åħĭç¦ı
    -0.06
    POSITIVE LOGITS
     means
    0.07
    éĢļ常æĺ¯
    0.07
    说æĺİ
    0.07
     presup
    0.07
    athan
    0.07
    ä½ĵçİ°åľ¨
    0.07
     typically
    0.07
    еÑĨ
    0.07
    ä¸Ĭ个
    0.06
    #@
    0.06
    Activations Density 0.010%

    No Known Activations