© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19724
    Prev
    Next
    INDEX
    Explanations

    but followed by contrast

    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
    ement
    -0.06
    çĭ±
    -0.06
    éĩįè¦ģäºĨ
    -0.06
    зов
    -0.06
    apis
    -0.05
    ä¸ĩå²ģ
    -0.05
    é½IJ
    -0.05
    ä½ĵå¤ĸ
    -0.05
    /functions
    -0.05
    èĥ½æľī
    -0.05
    POSITIVE LOGITS
    guer
    0.06
    æŶéĹ´åĨħ
    0.06
    çĢ
    0.06
    ensive
    0.05
    _constraints
    0.05
     realities
    0.05
    Reality
    0.05
    _constraint
    0.05
     Codes
    0.05
    æ¯ı天æĻļä¸Ĭ
    0.05
    Activations Density 0.003%

    No Known Activations