© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19227
    Prev
    Next
    INDEX
    Explanations

    command line options

    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
    /her
    -0.07
    ationally
    -0.07
    ation
    -0.07
    Ø©
    -0.07
    stin
    -0.06
    ature
    -0.06
    ated
    -0.06
    ãģ¾ãģ¾
    -0.06
    à¥įà¤Ł
    -0.06
    à¹Ī
    -0.06
    POSITIVE LOGITS
    avant
    0.07
    euros
    0.06
    ãģŁãĤī
    0.06
    ossier
    0.06
    afür
    0.06
     doubt
    0.06
    گاÙĩ
    0.06
    partment
    0.06
    espóÅĤ
    0.06
    à¸ģลาà¸ĩ
    0.06
    Activations Density 0.036%

    No Known Activations