© 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. 18105
    Prev
    Next
    INDEX
    Explanations

    contrasting clauses

    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
    ate
    -0.06
    /or
    -0.06
    usk
    -0.05
    oi
    -0.05
     Alternatively
    -0.05
    åİĦ
    -0.05
    æİ¥
    -0.05
    E
    -0.05
    ore
    -0.05
     Ðĺванов
    -0.05
    POSITIVE LOGITS
    iete
    0.06
    kla
    0.06
    ustru
    0.06
    æ¡¥æŀ¶
    0.06
    èĵĭ
    0.06
     whereas
    0.06
    }</
    0.06
    }',
    0.06
    roso
    0.06
    ÏĦίαÏĤ
    0.06
    Activations Density 0.011%

    No Known Activations