© 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. 40965
    Prev
    Next
    INDEX
    Explanations

    isomorphic or equivalent

    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
    мали
    -0.08
    è¾Ł
    -0.07
    orum
    -0.07
    è§Ī
    -0.07
    iskey
    -0.07
    ++,
    -0.07
    reeze
    -0.07
    ForKey
    -0.07
    éĩĩ纳çİĩ
    -0.06
    isper
    -0.06
    POSITIVE LOGITS
    æĹłåij³
    0.08
     thru
    0.07
    icho
    0.07
     بÙĬر
    0.07
    ecure
    0.07
     titolare
    0.07
    hid
    0.07
    ian
    0.07
    راÙĩ
    0.07
    ukat
    0.06
    Activations Density 0.007%

    No Known Activations