© 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. 50695
    Prev
    Next
    INDEX
    Explanations

    -1 as default or condition

    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
    bez
    -0.08
    rel
    -0.07
    orten
    -0.07
    ãĤ±
    -0.07
     occup
    -0.06
    inas
    -0.06
    Tan
    -0.06
     headed
    -0.06
    ken
    -0.06
    ols
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.10
    naan
    0.10
    iple
    0.08
    åħ°å¾·
    0.08
    jan
    0.07
    _PARSE
    0.07
    eing
    0.07
    ivirus
    0.07
    æĭīå°Ķ
    0.07
    immer
    0.07
    Activations Density 0.007%

    No Known Activations