© 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. 20860
    Prev
    Next
    INDEX
    Explanations

    questions or queries

    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
    aruh
    -0.07
    erals
    -0.06
    ợ
    -0.06
    æľīçĪ±
    -0.06
     dubb
    -0.06
    éĢīåŀĭ
    -0.06
    好货
    -0.06
    è¡¥çŁŃ
    -0.06
    emet
    -0.06
    GINE
    -0.06
    POSITIVE LOGITS
    ä¸į离
    0.07
    éĴĪ对
    0.06
    !
    0.05
    åŁºäºİ
    0.05
    !"
    0.05
    inen
    0.05
    kin
    0.05
    egna
    0.04
     specific
    0.04
     based
    0.04
    Activations Density 0.002%

    No Known Activations