© 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. 17911
    Prev
    Next
    INDEX
    Explanations

    technical actions or code verbs

    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
     and
    -0.06
    ht
    -0.05
     Rép
    -0.05
    åºĶè¿IJ
    -0.05
    ellan
    -0.05
     consape
    -0.05
     ÙģرÙĨ
    -0.05
     нез
    -0.05
     и
    -0.05
     zy
    -0.05
    POSITIVE LOGITS
    éĢļè¿ĩåĪĨæŀIJ
    0.06
    éĢļè¿ĩ使çĶ¨
    0.06
    è¡Ģ常è§Ħ
    0.06
    éĢļè¿ĩå°Ĩ
    0.06
    ondo
    0.06
    éĢļè¿ĩ
    0.05
    家åĸ»
    0.05
    alen
    0.05
    éĢļè¿ĩåľ¨
    0.05
    zem
    0.05
    Activations Density 0.027%

    No Known Activations