© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19364
    Prev
    Next
    INDEX
    Explanations

    review, alert, update, commentary

    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
    uson
    -0.06
    é¹°
    -0.05
    pn
    -0.05
     [~,
    -0.05
     syste
    -0.05
    aina
    -0.05
    ún
    -0.05
     regelmatig
    -0.05
    ain
    -0.05
    ector
    -0.05
    POSITIVE LOGITS
    ì¶ķ
    0.06
    å¸ĸ
    0.06
     pas
    0.06
    classic
    0.05
    ä¹ĭä¸ī
    0.05
    romise
    0.05
     اÙĦأط
    0.05
    imme
    0.05
     tri
    0.05
     Tri
    0.05
    Activations Density 0.329%

    No Known Activations