© 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. 3451
    Prev
    Next
    INDEX
    Explanations

    what happens when

    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
    å§ĭèĩ³ç»Ī
    -0.09
    satz
    -0.09
    erer
    -0.08
    erber
    -0.08
    aida
    -0.08
    åĵĶ
    -0.08
    anian
    -0.08
    ampton
    -0.08
    ìį¨
    -0.08
     Ñĥди
    -0.08
    POSITIVE LOGITS
    å®ŀå¤Ħ
    0.07
    ald
    0.07
    emos
    0.07
    uate
    0.07
    µ
    0.07
    ock
    0.07
    lah
    0.06
    osoph
    0.06
    åıijçĶŁæŶ
    0.06
    stance
    0.06
    Activations Density 0.046%

    No Known Activations