© 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. 21880
    Prev
    Next
    INDEX
    Explanations

    games of chance outcomes

    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
    éħ¸
    -0.06
    ONA
    -0.06
    jol
    -0.06
    çī§
    -0.05
     fulfil
    -0.05
    NOWLED
    -0.05
    ר׼
    -0.05
     fulfillment
    -0.05
     Comple
    -0.05
    ring
    -0.05
    POSITIVE LOGITS
    unie
    0.06
    追究åħ¶
    0.06
    binary
    0.05
    udem
    0.05
    天å°Ĭ
    0.05
     tradition
    0.05
    îte
    0.05
    å·²è¿ŀç»Ń
    0.05
    yek
    0.05
     consistency
    0.05
    Activations Density 0.004%

    No Known Activations