© 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. 42031
    Prev
    Next
    INDEX
    Explanations

    lists starting with 1

    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
    OUNT
    -0.07
    celli
    -0.07
    à´ķàµįà´ķàµį
    -0.07
    .nodeType
    -0.07
    åħ¼é¡¾
    -0.07
    ught
    -0.06
    nolog
    -0.06
    izont
    -0.06
     whence
    -0.06
    alse
    -0.06
    POSITIVE LOGITS
    æĢ§åľ°
    0.08
    оÑĩи
    0.08
    FromClass
    0.08
    irk
    0.07
    izr
    0.07
    æ´Ľå¤«
    0.07
    Sa
    0.07
     Redistributions
    0.07
    STONE
    0.07
    reland
    0.07
    Activations Density 0.036%

    No Known Activations