© 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. 19309
    Prev
    Next
    INDEX
    Explanations

    data from

    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
    scribe
    -0.07
    èĬ¹
    -0.07
    “She
    -0.06
    inek
    -0.06
    cribe
    -0.06
    halt
    -0.06
    segue
    -0.06
    voz
    -0.06
    itez
    -0.06
    tige
    -0.06
    POSITIVE LOGITS
    1
    0.05
     zin
    0.05
    '
    0.05
    ä¸Ĭä¸Ģ
    0.05
    er
    0.04
    æľīè´£
    0.04
    extr
    0.04
    æ£Ģè§Ĩ
    0.04
    --
    0.04
    0
    0.04
    Activations Density 0.009%

    No Known Activations