© 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. 60868
    Prev
    Next
    INDEX
    Explanations

    business model is similar

    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
     innoc
    -0.07
     Хаб
    -0.07
    oin
    -0.07
    åĵij
    -0.07
     Comments
    -0.07
    ante
    -0.07
     mant
    -0.07
    amework
    -0.06
    å·¥ä½ľäºĨ
    -0.06
     Hipp
    -0.06
    POSITIVE LOGITS
     بداÙĨ
    0.08
    ÙĦاÙĨ
    0.07
     Strand
    0.07
    ÑģÑĤÑĢÑı
    0.07
    .dense
    0.07
    _ALIAS
    0.06
    .abstract
    0.06
    KeyName
    0.06
    çĩ
    0.06
    alen
    0.06
    Activations Density 0.001%

    No Known Activations