© 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. 16995
    Prev
    Next
    INDEX
    Explanations

    it is

    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
    sing
    -0.05
    "While
    -0.05
    ิ
    -0.05
    èĬ±æŶéĹ´
    -0.05
    moz
    -0.05
    iz
    -0.05
     cod
    -0.05
    o
    -0.05
    “Our
    -0.05
    åħµ
    -0.05
    POSITIVE LOGITS
    eref
    0.06
    สาหà¸ģรรม
    0.06
    orce
    0.05
    çīĽè§Ĵ
    0.05
    ãģĭãģªãģĭãģ£ãģŁ
    0.05
    otov
    0.05
    _COMPLETED
    0.05
    rió
    0.05
    åįģåĪĨ
    0.05
    iful
    0.05
    Activations Density 0.006%

    No Known Activations