© 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. 29990
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License

    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
     Devils
    -0.09
    <|box_end|>
    -0.09
    å½ĵä¹ĭ
    -0.08
    iams
    -0.08
    almart
    -0.08
     lend
    -0.08
     Enemy
    -0.08
    Unnamed
    -0.08
    UED
    -0.07
    rano
    -0.07
    POSITIVE LOGITS
     GNU
    0.07
    geb
    0.07
    GNU
    0.07
    -gnu
    0.07
    ude
    0.06
    gez
    0.06
     forthcoming
    0.06
    ufs
    0.06
    en
    0.06
    irs
    0.06
    Activations Density 0.765%

    No Known Activations