© 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. 22822
    Prev
    Next
    INDEX
    Explanations

    associated with locations

    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
     sentido
    -0.07
    ád
    -0.07
    çĩĥ
    -0.07
    izo
    -0.07
    ison
    -0.06
    ãĤ¸ãĥ¼
    -0.06
    æ´¥
    -0.06
    enta
    -0.06
    åĨĩæľī
    -0.06
    Ñĥж
    -0.06
    POSITIVE LOGITS
    -related
    0.08
    -specific
    0.08
    åѦéĩij
    0.08
    -side
    0.08
    rame
    0.08
    dle
    0.08
    leden
    0.07
    ieme
    0.07
    -wide
    0.07
    ##_
    0.07
    Activations Density 0.672%

    No Known Activations