© 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. 17565
    Prev
    Next
    INDEX
    Explanations

    ability or capability

    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
    çĽ
    -0.05
    以å¾Ģ
    -0.05
    ion
    -0.05
    еÑĤ
    -0.05
    ius
    -0.05
    еÑģа
    -0.05
    è¿Ļä¸ĸä¸Ĭ
    -0.05
    akra
    -0.05
    ve
    -0.05
    æĪ´ç»´æĸ¯
    -0.05
    POSITIVE LOGITS
    ikk
    0.06
    fortun
    0.06
    fortunate
    0.06
    amai
    0.06
    hin
    0.06
    arczy
    0.05
    Too
    0.05
    olta
    0.05
    oram
    0.05
    æīĭæ³ķ
    0.05
    Activations Density 0.004%

    No Known Activations