© 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. 21307
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éłĨ
    -0.06
    иÑĤ
    -0.06
    eller
    -0.06
    æĹłæŃ¢
    -0.06
    oben
    -0.06
     voeren
    -0.05
    æķĸ
    -0.05
    anding
    -0.05
    agam
    -0.05
     foreseeable
    -0.05
    POSITIVE LOGITS
    oodle
    0.06
    boll
    0.05
    iene
    0.05
    åħ·
    0.05
    ÃŃp
    0.05
    ye
    0.05
     pair
    0.05
    gram
    0.05
    Passed
    0.05
    gia
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.