© 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. 19282
    Prev
    Next
    INDEX
    Explanations

    screen control sessions

    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
    æ¬ł
    -0.06
    .perform
    -0.06
    èĪ·
    -0.05
    iers
    -0.05
    ç»ĵå®ŀ
    -0.05
    çīĩçīĩ
    -0.05
    ensos
    -0.05
    ç¹ģ
    -0.05
    زش
    -0.05
    wich
    -0.05
    POSITIVE LOGITS
     share
    0.06
    çĽ¯èijĹ
    0.06
    迹
    0.06
    å¦ĻæĭĽ
    0.05
    prend
    0.05
    ä¸Ĭåı°
    0.05
    注åħ¥
    0.05
     traces
    0.05
     auft
    0.05
     takeover
    0.05
    Activations Density 0.016%

    No Known Activations