© 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. 20516
    Prev
    Next
    INDEX
    Explanations

    personalized text segments

    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
    é¡¹çĽ®è¿Ľè¡Į
    -0.05
    第äºĮæĿ¡
    -0.05
    å®ī康
    -0.05
    第äºĮç§į
    -0.05
    ниÑĨ
    -0.05
    lick
    -0.05
    å¤ļæĿ¡
    -0.05
    ÙĤÙĪÙĦ
    -0.05
    ibro
    -0.05
     Leist
    -0.05
    POSITIVE LOGITS
    ìĬµ
    0.05
    åºĶ交
    0.05
    eks
    0.05
    imente
    0.05
    ãĥĥãĤ¿ãĥ¼
    0.05
    设æ³ķ
    0.05
    é£İè¡Į
    0.05
    erche
    0.05
    andaag
    0.05
     Balt
    0.05
    Activations Density 0.014%

    No Known Activations