© 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. 48580
    Prev
    Next
    INDEX
    Explanations

    section headings and their follow-ups

    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
     either
    -0.07
    viously
    -0.07
    idget
    -0.07
    rastructure
    -0.07
    @gmail
    -0.07
    ipheral
    -0.07
    tection
    -0.07
    @email
    -0.07
    ordinator
    -0.06
    ä¸Ģæĺ¯
    -0.06
    POSITIVE LOGITS
     vs
    0.12
     же
    0.11
    oretical
    0.10
     versus
    0.10
    orem
    0.10
    åĭĩå¾Ģ缴åīį
    0.09
    .prototype
    0.08
    oret
    0.08
    èµ·è§ģ
    0.08
     inoltre
    0.08
    Activations Density 0.133%

    No Known Activations