© 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. 18458
    Prev
    Next
    INDEX
    Explanations

    here we go

    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
    ible
    -0.06
    æĺ§
    -0.06
    \C
    -0.05
    orium
    -0.05
    iver
    -0.05
    urable
    -0.05
    raven
    -0.05
     Complet
    -0.05
    ivers
    -0.05
    lands
    -0.05
    POSITIVE LOGITS
    æĺ¯ä¸Ģ个éĿŀ常
    0.06
    åĽłåľ°
    0.06
     inse
    0.06
    einander
    0.06
    eing
    0.06
    ause
    0.05
     being
    0.05
    omotive
    0.05
    èģĮä¸ļèµĦæł¼è¯ģ书
    0.05
    unjung
    0.05
    Activations Density 0.010%

    No Known Activations