© 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. 17745
    Prev
    Next
    INDEX
    Explanations

    code delimiters and abbreviations

    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
    isser
    -0.06
     :
    -0.05
    天天
    -0.05
     ;
    -0.05
    /or
    -0.05
     e
    -0.05
    ne
    -0.05
    åħ¶æŀĹ
    -0.04
     typically
    -0.04
     -
    -0.04
    POSITIVE LOGITS
    为äºĨç¡®ä¿Ŀ
    0.07
    ettor
    0.06
    为äºĨ
    0.06
    为äºĨèĥ½
    0.06
    ssia
    0.06
    Arguments
    0.06
    åij½
    0.06
     efectiv
    0.06
    ernet
    0.06
    ä½łçļĦå¿ĥ
    0.06
    Activations Density 0.050%

    No Known Activations