© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19176
    Prev
    Next
    INDEX
    Explanations

    scope and extent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    мееÑĤÑģÑı
    -0.07
    arial
    -0.06
    е
    -0.06
    arity
    -0.06
    agrams
    -0.06
     avid
    -0.06
    aye
    -0.06
    ار
    -0.06
    acks
    -0.06
    žel
    -0.06
    POSITIVE LOGITS
     scope
    0.09
     Scope
    0.09
     extent
    0.08
    èĮĥåĽ´
    0.07
    ç¯Ħåľį
    0.07
    Scope
    0.07
    (scope
    0.07
    èĮĥåĽ´çļĦ
    0.07
    weite
    0.06
    ç¯ĦåĽ²
    0.06
    Activations Density 0.011%

    No Known Activations