© 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. 17260
    Prev
    Next
    INDEX
    Explanations

    code syntax symbols and keywords

    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
    unan
    -0.06
    éĢĶ
    -0.06
     variables
    -0.06
    à¸Ńย
    -0.05
    -append
    -0.05
    dart
    -0.05
    å®īä¹IJ
    -0.05
     ðŁĶ
    -0.05
     Variables
    -0.05
    variables
    -0.05
    POSITIVE LOGITS
    emacs
    0.06
    вив
    0.06
    rom
    0.05
    ÑĪÑĤа
    0.05
    vertis
    0.05
    LEX
    0.05
    åıijèµ·
    0.05
    oret
    0.05
    ISIS
    0.05
    vro
    0.05
    Activations Density 0.240%

    No Known Activations