© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20008
    Prev
    Next
    INDEX
    Explanations

    respect your

    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
    åľ¨å²Ĺ
    -0.07
    ukum
    -0.06
     forfait
    -0.06
    anisme
    -0.06
    prat
    -0.06
    æ¼Ķä¹ī
    -0.06
    Memo
    -0.06
    ãĤıãģĸ
    -0.06
    nod
    -0.06
    没æľīåħ¶ä»ĸ
    -0.06
    POSITIVE LOGITS
    ically
    0.06
    ially
    0.06
    å·¦åı³çļĦ
    0.06
    ile
    0.05
    æĢ§åľ°
    0.05
    ↵
    0.05
    ely
    0.05
    0.05
    åĬĽçļĦ
    0.05
    fully
    0.05
    Activations Density 0.002%

    No Known Activations