© 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. 17082
    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
    enek
    -0.08
    许åı¯æĸĩ件
    -0.07
     burge
    -0.07
    éĢīä¸Ģ
    -0.07
    ydd
    -0.07
    digest
    -0.06
    庸
    -0.06
     Ause
    -0.06
    lj
    -0.06
    sha
    -0.06
    POSITIVE LOGITS
     C
    0.06
    /
    0.06
    -
    0.06
     P
    0.06
     R
    0.06
    0.05
     hypothesis
    0.05
     suppress
    0.05
     Confirm
    0.05
     B
    0.05
    Activations Density 0.000%

    No Known Activations