© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19374
    Prev
    Next
    INDEX
    Explanations

    Criminal Tattoo

    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
    ovin
    -0.06
    oz
    -0.06
    ettes
    -0.06
    ipes
    -0.06
    нок
    -0.06
     hang
    -0.05
    纷
    -0.05
     pono
    -0.05
    ải
    -0.05
    ette
    -0.05
    POSITIVE LOGITS
     rass
    0.06
    emet
    0.06
    çªĥ
    0.06
    é¡¹çĽ®è¿Ľè¡Į
    0.05
    erez
    0.05
    åĪĩãģ£ãģ¦
    0.05
    ר×Ķ
    0.05
    åı¦æľī
    0.05
    ambre
    0.05
    åīĩæĺ¯
    0.05
    Activations Density 0.001%

    No Known Activations