© 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. 20224
    Prev
    Next
    INDEX
    Explanations

    privileged access

    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
    éĺ³åħī
    -0.06
     doorway
    -0.05
     Sun
    -0.05
    åŁŁ
    -0.05
     concerned
    -0.05
    æķ£
    -0.05
    phinx
    -0.05
    ارة
    -0.05
    Sun
    -0.05
     Ange
    -0.05
    POSITIVE LOGITS
    alise
    0.06
    hta
    0.06
    ÃŃsmo
    0.06
    tiz
    0.06
     Empresarial
    0.06
    serviceName
    0.06
    çļĦæľįåĭĻ
    0.05
    pars
    0.05
    ago
    0.05
     az
    0.05
    Activations Density 0.003%

    No Known Activations