© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21501
    Prev
    Next
    INDEX
    Explanations

    steady growth and pace

    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
    اÙĭ
    -0.07
    s
    -0.06
     amp
    -0.06
    u
    -0.06
    imately
    -0.06
    ä¸Ĭ
    -0.06
    ations
    -0.06
    overs
    -0.06
    ively
    -0.06
    ëĤĺë§Ī
    -0.06
    POSITIVE LOGITS
    Ø©
    0.07
    碼
    0.07
    å¦Ĥå±±
    0.07
     tutur
    0.07
    olon
    0.07
    segue
    0.07
    igo
    0.06
    clid
    0.06
    egur
    0.06
    abat
    0.06
    Activations Density 0.004%

    No Known Activations