© 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. 18781
    Prev
    Next
    INDEX
    Explanations

    form, app, dis, inc, rec

    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
    adays
    -0.06
     **.**
    -0.06
    åıĪä¸Ģ个
    -0.06
    ложено
    -0.06
    adat
    -0.06
     اÙĦاÙĨÙģ
    -0.06
     katakan
    -0.06
    ldata
    -0.06
    kie
    -0.06
    flux
    -0.05
    POSITIVE LOGITS
    itude
    0.06
    ung
    0.05
    0.05
    inar
    0.05
    à¹Ģà¸ĩิà¸Ļ
    0.05
    ews
    0.05
    cium
    0.05
    ao
    0.05
     دادÙĨ
    0.05
    ify
    0.05
    Activations Density 0.004%

    No Known Activations