© 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. 21467
    Prev
    Next
    INDEX
    Explanations

    occasional or periodic events

    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
    agini
    -0.07
    stur
    -0.07
    aviour
    -0.06
    å§Ĩ
    -0.06
    esso
    -0.06
    ÙĬÙijØ©
    -0.06
    ried
    -0.06
    ght
    -0.06
    mino
    -0.06
    ungkin
    -0.06
    POSITIVE LOGITS
     backed
    0.05
    urence
    0.05
    omie
    0.05
    بØŃ
    0.05
    bod
    0.05
    веÑĢÑĪенÑģÑĤво
    0.05
    akes
    0.05
    udes
    0.05
    ésie
    0.05
     j
    0.05
    Activations Density 0.015%

    No Known Activations