© 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. 17405
    Prev
    Next
    INDEX
    Explanations

    numbers or INITIAL

    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
    iguez
    -0.07
    euw
    -0.07
    ereitung
    -0.07
     clientela
    -0.06
    sortable
    -0.06
    ordio
    -0.06
    ترÙĪÙĦ
    -0.06
    ponce
    -0.06
    å©·
    -0.06
    rossover
    -0.06
    POSITIVE LOGITS
    er
    0.05
     layer
    0.05
    elt
    0.05
     pen
    0.05
    ak
    0.05
     t
    0.05
    uk
    0.05
    ians
    0.05
    -
    0.05
     T
    0.05
    Activations Density 0.027%

    No Known Activations