© 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. 19114
    Prev
    Next
    INDEX
    Explanations

    variable names

    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
    è¹
    -0.06
    å¦Ĥåħ¶
    -0.05
     detr
    -0.05
    åķ¼
    -0.05
    els
    -0.05
    åĥ
    -0.05
    iken
    -0.05
     stem
    -0.05
    å®Ľ
    -0.05
    eit
    -0.04
    POSITIVE LOGITS
    ÅĤÄĻ
    0.07
    vky
    0.06
     Toll
    0.06
    yth
    0.06
    çľ¼äºĨ
    0.06
    æĦŁæģ©çļĦå¿ĥ
    0.06
    åĨħéĥ¨
    0.06
    arde
    0.06
    yec
    0.06
     пÑĢиз
    0.06
    Activations Density 0.001%

    No Known Activations