© 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. 22076
    Prev
    Next
    INDEX
    Explanations

    punctuation and word beginnings

    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
    опо
    -0.06
    onom
    -0.06
    çĦ¶
    -0.06
    ilers
    -0.06
    ah
    -0.05
    ä¸įçĿĢ
    -0.05
    ue
    -0.05
    Ñģпеди
    -0.05
    dach
    -0.05
    ono
    -0.05
    POSITIVE LOGITS
    atia
    0.07
     vét
    0.06
    assi
    0.06
    urga
    0.06
     levantamento
    0.06
    æĸĩå±±
    0.06
    udging
    0.06
     ëį§ë¶ĻìĺĢëĭ¤
    0.05
     Yo
    0.05
    erala
    0.05
    Activations Density 0.550%

    No Known Activations