© 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. 18468
    Prev
    Next
    INDEX
    Explanations

    null or null pointer

    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
     Äijặn
    -0.07
    éĽį
    -0.06
    artment
    -0.05
    곡
    -0.05
    andes
    -0.05
    odin
    -0.05
    /out
    -0.05
    amt
    -0.05
    haupt
    -0.05
    ahrungs
    -0.05
    POSITIVE LOGITS
    worthy
    0.07
    eer
    0.06
    رس
    0.06
    cion
    0.06
    mium
    0.06
    ุà¸Ķิà¸ļ
    0.06
    s
    0.06
    tä
    0.06
    ÙĬبة
    0.06
    cü
    0.06
    Activations Density 0.011%

    No Known Activations