© 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
    2. Qwen3.5-4B
    3. 15-RES-MATRYOSHKA-65K
    4. 21210
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
    olumn
    -0.05
    Segment
    -0.05
    大åįĥ
    -0.05
    æµģæ°´
    -0.05
    aan
    -0.05
    беÑĢе
    -0.05
    ernaut
    -0.05
     complained
    -0.05
    èµ¶
    -0.05
    itter
    -0.05
    POSITIVE LOGITS
    +:
    0.06
    ?):
    0.06
    )":
    0.05
    .):
    0.05
    ège
    0.05
    tru
    0.05
    irian
    0.05
    +)/
    0.05
     met
    0.05
     seme
    0.05
    Activations Density 0.001%

    No Known Activations