© 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. 17149
    Prev
    Next
    INDEX
    Explanations

    use an extraction utility

    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
    langen
    -0.05
    éĩİ
    -0.05
    rq
    -0.05
     mal
    -0.05
     Mand
    -0.05
    åĬ¨
    -0.05
    enko
    -0.05
    omic
    -0.05
    åĪ«
    -0.05
    çī¹æ®Ĭ
    -0.05
    POSITIVE LOGITS
    udent
    0.07
    kut
    0.06
    tores
    0.06
    iru
    0.06
    UDENT
    0.06
    icule
    0.06
    æݧåĪ¶æĬĢæľ¯
    0.06
    çī©çļĦ
    0.06
    uely
    0.06
    мени
    0.06
    Activations Density 0.018%

    No Known Activations