© 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. 20162
    Prev
    Next
    INDEX
    Explanations

    sql column names like id or status

    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
    quer
    -0.06
    å±ħ
    -0.05
    FromString
    -0.05
    δι
    -0.05
    rest
    -0.05
    ä¹ĭåīįçļĦ
    -0.05
     Onze
    -0.05
     ï¼Ī
    -0.05
    ä¹ĭåīį
    -0.05
    ина
    -0.05
    POSITIVE LOGITS
    ÙĨاÙĩ
    0.06
    人åħ³æ³¨
    0.06
     éve
    0.06
    ä¸įé«ĺåħ´
    0.06
    æİĪæĿĥ使çĶ¨
    0.06
    eton
    0.06
    人è´Ńä¹°
    0.06
    impat
    0.05
    olto
    0.05
    _ty
    0.05
    Activations Density 0.019%

    No Known Activations