© 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. 56900
    Prev
    Next
    INDEX
    Explanations

    comments following "p"

    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
    hop
    -0.08
    InlineData
    -0.08
    StartupScript
    -0.08
    SetBranch
    -0.08
    rach
    -0.08
    iglia
    -0.08
    VMLINUX
    -0.07
    FOUND
    -0.07
    loh
    -0.07
    allinen
    -0.07
    POSITIVE LOGITS
    seealso
    0.08
     Cave
    0.08
    注
    0.08
    åıĤéĺħ
    0.07
     See
    0.07
    See
    0.07
    see
    0.07
     Intern
    0.07
     {@
    0.06
     [`
    0.06
    Activations Density 0.191%

    No Known Activations