© 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. 21316
    Prev
    Next
    INDEX
    Explanations

    **Affirmation or possibility detection**

    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
    owitz
    -0.07
    çļ®
    -0.06
    ç«ł
    -0.06
    :)
    -0.05
    ell
    -0.05
    ÑģпоÑĢÑĤа
    -0.05
    indh
    -0.05
    afs
    -0.05
    ekh
    -0.05
     periód
    -0.05
    POSITIVE LOGITS
    же
    0.07
     otherwise
    0.05
     Nass
    0.05
    ãģĮãģ¤
    0.05
    ãģ§ãģįãĤĮãģ°
    0.05
    itkan
    0.05
     spite
    0.05
     com
    0.05
    Ñģпе
    0.05
    respect
    0.05
    Activations Density 0.011%

    No Known Activations