© 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. 18786
    Prev
    Next
    INDEX
    Explanations

    member of

    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
    киÑģло
    -0.08
    GING
    -0.07
    irman
    -0.07
     !_
    -0.07
    кÑĢема
    -0.07
    IVID
    -0.07
    вÑĤÑĢа
    -0.07
    kannya
    -0.07
    klen
    -0.07
    没æĥ³åĪ°
    -0.07
    POSITIVE LOGITS
    ieke
    0.06
    ized
    0.05
    ically
    0.05
     juxtap
    0.05
    eric
    0.05
     contrast
    0.05
     fact
    0.05
    0.05
    ter
    0.05
     polar
    0.05
    Activations Density 0.040%

    No Known Activations