© 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. 17596
    Prev
    Next
    INDEX
    Explanations

    `adv` followed by `ices`

    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
    sense
    -0.06
    andel
    -0.06
    irsch
    -0.06
     بÙĤÙĬادة
    -0.06
    å®ļ
    -0.06
    èĤ¿çĺ¤åĮ»éĻ¢
    -0.05
    sel
    -0.05
    odle
    -0.05
    aji
    -0.05
     gefallen
    -0.05
    POSITIVE LOGITS
    uler
    0.06
    åį§
    0.06
    енÑĮ
    0.06
     worsh
    0.05
    гда
    0.05
    ÙĩÙĨ
    0.05
    çļĦæĺ¯
    0.05
    zs
    0.05
    jou
    0.05
    ulta
    0.05
    Activations Density 0.005%

    No Known Activations