© 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. 18332
    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
    ael
    -0.05
    åľ°
    -0.05
     alternate
    -0.05
    aa
    -0.05
    oric
    -0.05
    形容
    -0.05
    ä¹ĥ
    -0.05
    äºĪ
    -0.05
    ire
    -0.05
    Alternate
    -0.05
    POSITIVE LOGITS
    ASF
    0.07
    iform
    0.06
    undas
    0.06
    utsch
    0.06
    ntag
    0.06
    epat
    0.06
    绣
    0.06
    posa
    0.06
    éĩįæĭħ
    0.06
    егда
    0.06
    Activations Density 0.000%

    No Known Activations