© 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. 20972
    Prev
    Next
    INDEX
    Explanations

    author of

    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
     vare
    -0.06
    arrêt
    -0.06
     ÑģоÑĢ
    -0.06
     Dere
    -0.06
     Bren
    -0.06
    ÑģоÑĢ
    -0.06
     troub
    -0.06
    spath
    -0.05
    åīįåİ»
    -0.05
    go
    -0.05
    POSITIVE LOGITS
    abor
    0.06
    laub
    0.06
     sense
    0.05
    addin
    0.05
    jab
    0.05
    ÙĬاب
    0.05
    itin
    0.05
     dem
    0.05
    åĪĨæĺİ
    0.05
    主人ç¿ģ
    0.05
    Activations Density 0.010%

    No Known Activations