© 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. 19089
    Prev
    Next
    INDEX
    Explanations

    move forward, completion, possible

    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
     ÑģпÑĢÑı
    -0.06
     supl
    -0.06
    æĢĿç»´çļĦ
    -0.06
    è·Łè¸ª
    -0.05
    enses
    -0.05
    arczy
    -0.05
    pire
    -0.05
    _tracking
    -0.05
    tracking
    -0.05
    gara
    -0.05
    POSITIVE LOGITS
     stalled
    0.07
    åıĹéĺ»
    0.06
    uro
    0.06
     prerequisite
    0.06
     incomplete
    0.06
    æīįèĥ½çľŁæŃ£
    0.06
    æĿŁ
    0.06
    æľªå®ĮæĪIJ
    0.06
     cannot
    0.06
    Completion
    0.06
    Activations Density 0.219%

    No Known Activations