© 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. 20949
    Prev
    Next
    INDEX
    Explanations

    suggest adding a

    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
    оне
    -0.06
    nos
    -0.06
    inance
    -0.05
    à¸ĭà¹Į
    -0.05
    æľĽ
    -0.05
    ÑĢÑıд
    -0.05
    çĥ¨
    -0.05
    onto
    -0.05
    çĨı
    -0.05
    æ²ī
    -0.05
    POSITIVE LOGITS
    ÙĤÙĬÙĤÙĬ
    0.06
    ä»Ģä¹Īåij¢
    0.06
    ?,?,?,?,
    0.06
    å±ħæīĢ
    0.06
    بÙĬØ©
    0.06
    ç²ķ
    0.06
    itious
    0.06
    PELL
    0.05
    ä»Ģ麽
    0.05
     fundamentals
    0.05
    Activations Density 0.004%

    No Known Activations