© 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. 21473
    Prev
    Next
    INDEX
    Explanations

    barking at things

    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
     prest
    -0.05
    èĦĬæ¤İ
    -0.05
    aku
    -0.05
     respected
    -0.05
    aji
    -0.05
    á»Ĺ
    -0.05
     instinct
    -0.05
     biom
    -0.05
    ield
    -0.05
    uck
    -0.05
    POSITIVE LOGITS
    osat
    0.07
    yed
    0.07
    ostas
    0.07
    æ³Ľ
    0.06
     excit
    0.06
    Ùħرت
    0.06
    åĴĮéľĢæ±Ĥ
    0.06
    gara
    0.06
    ønn
    0.06
    /Edit
    0.06
    Activations Density 0.005%

    No Known Activations