© 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. 18206
    Prev
    Next
    INDEX
    Explanations

    focus on

    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
    Beat
    -0.07
    rit
    -0.06
    å®ŀå¤Ħ
    -0.06
    迹
    -0.06
     abstract
    -0.06
     beat
    -0.06
    è¹Ł
    -0.06
     Beat
    -0.06
     beats
    -0.05
    åĬ¨åĬĽæĸ¹éĿ¢
    -0.05
    POSITIVE LOGITS
    .LENGTH
    0.06
    anes
    0.05
    éľĸ
    0.05
    ÙĪØ·
    0.05
    ivery
    0.05
    å¦ĤåIJĮä¸Ģ
    0.05
    ×ķת
    0.05
     anci
    0.05
    -short
    0.05
    Eye
    0.05
    Activations Density 0.003%

    No Known Activations