© 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. 19245
    Prev
    Next
    INDEX
    Explanations

    Core tip

    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
    uder
    -0.07
    uds
    -0.06
    cling
    -0.06
     convocatoria
    -0.06
    ×IJ×ķת
    -0.06
    ubb
    -0.06
    ára
    -0.05
     vicepresidente
    -0.05
    yj
    -0.05
     Bevor
    -0.05
    POSITIVE LOGITS
    åĪĿ
    0.05
    åĪĿ次
    0.05
    个ä½ĵ
    0.05
    imal
    0.05
    価
    0.05
     =='
    0.05
    ingan
    0.05
     privilege
    0.05
     struggles
    0.05
    estr
    0.05
    Activations Density 0.001%

    No Known Activations