© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21622
    Prev
    Next
    INDEX
    Explanations

    illustrative examples

    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
    çĶ¨
    -0.06
    ø
    -0.05
    jam
    -0.05
    çĶ¨å®ĥ
    -0.05
    oras
    -0.05
    aby
    -0.05
    çĶ¨ä¸Ģ个
    -0.05
    .Comparator
    -0.05
    бÑĥÑģ
    -0.05
    ï¼Ī
    -0.05
    POSITIVE LOGITS
    apr
    0.07
    trad
    0.06
    ieden
    0.06
    åľ°å¤Ħ
    0.06
     illet
    0.06
    äºĨä¸Ģè·³
    0.06
    缮çļĦåľ¨äºİ
    0.06
     ÑĤов
    0.06
    ืà¹īà¸Ń
    0.06
    -IS
    0.06
    Activations Density 0.036%

    No Known Activations