© 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. 30888
    Prev
    Next
    INDEX
    Explanations

    programming element selectors

    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
    els
    -0.07
    ़
    -0.07
    estig
    -0.07
    çĥĪçĦ°
    -0.07
    etailed
    -0.07
    yer
    -0.07
    illing
    -0.06
    к
    -0.06
    ças
    -0.06
    ellaneous
    -0.06
    POSITIVE LOGITS
    wise
    0.11
    ials
    0.11
    ially
    0.10
    halb
    0.10
    ized
    0.10
    ymology
    0.09
    alist
    0.09
    arily
    0.09
    izabeth
    0.09
    /disable
    0.09
    Activations Density 0.046%

    No Known Activations