© 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. 17386
    Prev
    Next
    INDEX
    Explanations

    html id attribute

    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
    er
    -0.08
    erer
    -0.06
    inga
    -0.06
     ÑģодеÑĢжа
    -0.05
    ing
    -0.05
    oka
    -0.05
    åĨħ涵
    -0.05
    a
    -0.05
    Ø©
    -0.05
     Zuletzt
    -0.05
    POSITIVE LOGITS
    undle
    0.07
    /close
    0.07
    moi
    0.07
    vecs
    0.07
    thinkable
    0.06
    @",
    0.06
    dade
    0.06
     **—
    0.06
     ÐĶиза
    0.06
    pare
    0.06
    Activations Density 0.036%

    No Known Activations