© 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. 22134
    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
    sWith
    -0.07
    ishes
    -0.06
    impresa
    -0.06
    ner
    -0.06
    ymes
    -0.06
    micas
    -0.06
    éns
    -0.06
    imps
    -0.06
     calci
    -0.06
    ostra
    -0.06
    POSITIVE LOGITS
    çĮĽåľ°
    0.05
    åĨ¥
    0.05
    è£ħåľ¨
    0.05
    oros
    0.05
    éĩį
    0.05
    ©
    0.05
     Personal
    0.05
    personal
    0.04
    zonder
    0.04
     Lyc
    0.04
    Activations Density 0.000%

    No Known Activations