© 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. 2690
    Prev
    Next
    INDEX
    Explanations

    street names and numbers

    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
    ály
    -0.08
    alis
    -0.07
    asaki
    -0.07
    andbox
    -0.07
    Äģl
    -0.06
    èĹ©
    -0.06
    alin
    -0.06
    .sym
    -0.06
    ynd
    -0.06
    è¶Ĭéķ¿
    -0.06
    POSITIVE LOGITS
    æľĿ
    0.08
    åĵĪæĭī
    0.08
    æī¹åĩĨ
    0.07
    áĢ²
    0.07
    涧
    0.07
    atico
    0.07
    stit
    0.07
    atica
    0.07
     unm
    0.07
     hor
    0.07
    Activations Density 0.092%

    No Known Activations