© 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. 20644
    Prev
    Next
    INDEX
    Explanations

    Ignore predictions or read more

    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
    abu
    -0.06
    вил
    -0.05
     Whisper
    -0.05
    åľ¨åį³
    -0.05
    alth
    -0.05
    ehrt
    -0.05
    åħ³å¤´
    -0.05
     Wizard
    -0.05
    èĬ®
    -0.05
    ä½ĵç³»
    -0.05
    POSITIVE LOGITS
    æµģ
    0.07
    çļĦæĹ¥å¸¸
    0.06
    åħĪçĥĪ
    0.06
    ochen
    0.06
    kev
    0.06
    cha
    0.06
    æĹ¥å¸¸
    0.06
     susp
    0.05
    åľ¨æŃ¤æľŁéĹ´
    0.05
    IED
    0.05
    Activations Density 0.005%

    No Known Activations