© 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. 19165
    Prev
    Next
    INDEX
    Explanations

    None, false, or empty values

    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
    yrı
    -0.06
    edom
    -0.06
     caer
    -0.06
     Gram
    -0.05
    /bus
    -0.05
    chie
    -0.05
    friend
    -0.05
    order
    -0.05
     bì
    -0.05
     ca
    -0.05
    POSITIVE LOGITS
     things
    0.05
    rought
    0.05
    variably
    0.05
    å°ijæľī
    0.05
    rels
    0.05
    á»ijc
    0.05
    _No
    0.05
    éĻ©
    0.05
    å¼ķåħ¥
    0.05
     concessions
    0.05
    Activations Density 0.016%

    No Known Activations