© 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. 22176
    Prev
    Next
    INDEX
    Explanations

    Pagan, magic, occult, age

    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
    éķ¿
    -0.05
     ir
    -0.05
    —
    -0.05
     revenue
    -0.05
     long
    -0.05
     mam
    -0.05
    bu
    -0.05
    éķ·
    -0.05
    sf
    -0.04
    ent
    -0.04
    POSITIVE LOGITS
    wod
    0.07
    erbe
    0.07
    andat
    0.07
     importe
    0.07
    erset
    0.07
    andest
    0.06
    venta
    0.06
    å®ŀéĻħæݧåĪ¶æĿĥ
    0.06
    йо
    0.06
    .Middle
    0.06
    Activations Density 0.022%

    No Known Activations