© 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. 20136
    Prev
    Next
    INDEX
    Explanations

    attorney or lawyer

    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
    ärke
    -0.07
     Acompan
    -0.06
    оеди
    -0.06
    dej
    -0.06
    pare
    -0.06
    ordinator
    -0.06
    pf
    -0.05
     Alter
    -0.05
    æĥ¯
    -0.05
    ran
    -0.05
    POSITIVE LOGITS
    unde
    0.07
    ulen
    0.06
    ilde
    0.06
    uchi
    0.06
    iger
    0.06
    Ñħом
    0.06
    werbung
    0.05
    ches
    0.05
    ullah
    0.05
    zimmer
    0.05
    Activations Density 0.025%

    No Known Activations