© 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. 22060
    Prev
    Next
    INDEX
    Explanations

    place names or entities

    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
    lässigkeit
    -0.06
    ãģ«è¡Įãģ£ãģ¦ãģįãģ¾ãģĹãģŁ
    -0.06
    ;**
    -0.06
    inage
    -0.06
    书页
    -0.06
    eté
    -0.06
    iture
    -0.05
    Å¡ov
    -0.05
    utki
    -0.05
    estr
    -0.05
    POSITIVE LOGITS
    avn
    0.06
    bab
    0.05
    -minus
    0.05
    nam
    0.05
    åĭĻ
    0.05
    ac
    0.05
    '
    0.05
    å°¾
    0.05
    å½¹
    0.05
    ful
    0.05
    Activations Density 0.004%

    No Known Activations