© 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. 21038
    Prev
    Next
    INDEX
    Explanations

    device followed by certain words

    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
    erait
    -0.08
    stin
    -0.08
    äºĭåįĬåĬŁåĢį
    -0.07
    onstruk
    -0.07
    erer
    -0.07
    çĤ¹æѤ
    -0.07
    æĪĸå¤ļ
    -0.07
    ležitost
    -0.07
     début
    -0.07
    çĦ¶å¤§
    -0.07
    POSITIVE LOGITS
    ity
    0.08
    burn
    0.05
    ius
    0.05
    оÑĤ
    0.05
    دÙĩ
    0.05
    त
    0.05
    è°·
    0.05
    ev
    0.05
    el
    0.05
    itin
    0.05
    Activations Density 0.049%

    No Known Activations