© 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. 19962
    Prev
    Next
    INDEX
    Explanations

    debt, loans, and credit card terms

    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
    åıijå±ķ壮大
    -0.07
     rob
    -0.06
    udar
    -0.06
     Hindered
    -0.06
    skirts
    -0.06
    é¢ĸ
    -0.06
    亢
    -0.06
    å¾·æīį
    -0.06
     supre
    -0.06
    umo
    -0.06
    POSITIVE LOGITS
    åĽ´æĶ»
    0.06
     targeted
    0.06
    ียว
    0.05
    au
    0.05
    ÃŁer
    0.05
    çģ«å±±
    0.05
     priorit
    0.05
    ingles
    0.05
     Levine
    0.05
    tract
    0.05
    Activations Density 0.007%

    No Known Activations