© 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. 17380
    Prev
    Next
    INDEX
    Explanations

    the followed by a noun

    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
    }
    -0.05
    -0.05
    ]
    -0.05
    1
    -0.05
    2
    -0.05
    ization
    -0.05
    )
    -0.05
    å®Į
    -0.05
    è¿Ļ个
    -0.04
    ora
    -0.04
    POSITIVE LOGITS
    å±ħå¤ļ
    0.08
    dua
    0.07
    uletzt
    0.07
    ellow
    0.07
    ály
    0.07
    ocas
    0.07
    redis
    0.07
    forte
    0.07
    UFF
    0.07
    ewan
    0.07
    Activations Density 0.035%

    No Known Activations