© 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. 47860
    Prev
    Next
    INDEX
    Explanations

    forests and related environments

    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
    zahl
    -0.08
     domicili
    -0.08
    ä¸Ĭ人
    -0.08
     acom
    -0.08
    osition
    -0.08
    ylum
    -0.08
    geber
    -0.07
    erator
    -0.07
    åĽŀäºĭ
    -0.07
    oriously
    -0.07
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.10
    æ·±å¤ĦçļĦ
    0.09
    å¯Ĩå¸ĥ
    0.08
     canopy
    0.08
    èħ¹åľ°
    0.08
    ablish
    0.08
    ières
    0.07
    wide
    0.07
     плоÑīадÑĮÑİ
    0.07
     dense
    0.07
    Activations Density 0.040%

    No Known Activations