© 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. 17090
    Prev
    Next
    INDEX
    Explanations

    expensive technology and materials

    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
    å±ĬæŶ
    -0.06
     greater
    -0.06
    å¦Ĥæŀľ
    -0.05
    kadang
    -0.05
    å¦Ĥæŀľå¯¹
    -0.05
     Brush
    -0.05
    mtree
    -0.05
    械
    -0.05
    ersh
    -0.05
    èĵī
    -0.05
    POSITIVE LOGITS
     puro
    0.06
    uma
    0.06
    elian
    0.06
     pura
    0.06
    设å¤ĩåĪ¶éĢł
    0.06
    аÑĤÑĥ
    0.06
    acists
    0.06
    令人
    0.06
    uchtigkeit
    0.06
    lement
    0.05
    Activations Density 0.012%

    No Known Activations