© 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. 17984
    Prev
    Next
    INDEX
    Explanations

    strings with punctuation and special characters

    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
    bol
    -0.07
    æĸ¹åľĨ
    -0.06
    Targets
    -0.05
     reck
    -0.05
     chặt
    -0.05
    irmingham
    -0.05
    anos
    -0.05
     markers
    -0.05
     curs
    -0.05
    ç²Ĺçķ¥
    -0.04
    POSITIVE LOGITS
    оÑĢо
    0.06
    iffe
    0.06
    emps
    0.06
    éĻIJ
    0.05
     sung
    0.05
    orb
    0.05
    å®ŀåľ°
    0.05
    äºĶ次
    0.05
    impin
    0.05
    rove
    0.05
    Activations Density 0.007%

    No Known Activations