© 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. 27708
    Prev
    Next
    INDEX
    Explanations

    APPEALSPETITIONreviewed

    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
    à¸Ĭล
    -0.08
    acements
    -0.08
    aint
    -0.08
    ÅŁa
    -0.07
    æľĢæĸ°æĸĩç«ł
    -0.07
    itos
    -0.07
    ä¸Ģéĺµéĺµ
    -0.07
    ÑĤеа
    -0.07
    ÙĦاغ
    -0.07
    abilities
    -0.07
    POSITIVE LOGITS
    åłĤçļĦ
    0.08
    éĺ¿æĭī伯
    0.07
    å®ŀå¤Ħ
    0.07
    ิรà¹Į
    0.07
    åĬłæĭ¿å¤§
    0.07
    ommel
    0.06
    俱ä¹IJéĥ¨
    0.06
    并èĮĤ
    0.06
    èı©
    0.06
    stattung
    0.06
    Activations Density 0.010%

    No Known Activations