© 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. 30356
    Prev
    Next
    INDEX
    Explanations

    start of sentences

    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
    以åıĬä¸ĢäºĽ
    -0.07
     actually
    -0.07
    è¿ĺ没æľī
    -0.06
    iev
    -0.06
    .ly
    -0.06
     (::
    -0.06
     (!$
    -0.06
    eschi
    -0.06
     пÑĢодÑĥ
    -0.06
     Obst
    -0.06
    POSITIVE LOGITS
    çĻ¾ä½Ļ
    0.07
    .configure
    0.07
    outers
    0.07
    agger
    0.07
    ottom
    0.07
     Doch
    0.07
    baugh
    0.07
    oola
    0.07
    ÑĢоÑģ
    0.07
    欢声
    0.07
    Activations Density 0.036%

    No Known Activations