© 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. 19186
    Prev
    Next
    INDEX
    Explanations

    login to

    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
    acked
    -0.08
    acks
    -0.07
    ارد
    -0.06
    chaft
    -0.06
    ack
    -0.06
    itez
    -0.06
    erade
    -0.06
    ITIES
    -0.06
    त
    -0.06
    ÙĪÙĪ
    -0.06
    POSITIVE LOGITS
    orten
    0.05
    eman
    0.05
    usher
    0.05
    ëľ
    0.05
    çĶ¨è½¦
    0.05
    ib
    0.05
     **.**
    0.05
    产åĵģä¸Ńå¿ĥ
    0.05
     Danach
    0.05
    wner
    0.05
    Activations Density 0.008%

    No Known Activations