© 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. 17152
    Prev
    Next
    INDEX
    Explanations

    portfolio-related financial or creative content

    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
    à¹Ĩ
    -0.06
     à¹Ĩ
    -0.06
    amad
    -0.05
    ities
    -0.05
    zinha
    -0.05
    رÙĪÙĬ
    -0.05
    ube
    -0.05
    жкой
    -0.05
    ly
    -0.05
    -packed
    -0.05
    POSITIVE LOGITS
    owie
    0.07
    aux
    0.06
    ed
    0.06
    à¹Ħมà¹ī
    0.06
    presidente
    0.06
     Silv
    0.06
    imonial
    0.06
    æĪIJ交
    0.06
    ÑģÑĤÑĭÑħ
    0.06
    ÑĭÑħ
    0.06
    Activations Density 0.005%

    No Known Activations