© 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. 21649
    Prev
    Next
    INDEX
    Explanations

    'apos' followed by x

    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
    çº
    -0.07
    äºļ
    -0.06
    gege
    -0.06
    aight
    -0.06
    ifer
    -0.05
     candidature
    -0.05
     باÙĦا
    -0.05
    å¯ĦçĶŁ
    -0.05
     Permit
    -0.05
     Weiner
    -0.05
    POSITIVE LOGITS
    èĦ¸
    0.06
     oms
    0.05
     Gau
    0.05
     dis
    0.05
     gro
    0.05
    Nr
    0.05
     abuse
    0.05
    nameof
    0.05
     rec
    0.05
     abst
    0.05
    Activations Density 0.001%

    No Known Activations