© 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. 21484
    Prev
    Next
    INDEX
    Explanations

    body parts and structures

    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
     headed
    -0.05
     souhaitent
    -0.05
    led
    -0.05
    -l
    -0.05
    ä¸ľè¥¿
    -0.05
     -
    -0.04
     Afinal
    -0.04
    ì¶ķ
    -0.04
    given
    -0.04
    appa
    -0.04
    POSITIVE LOGITS
    brero
    0.06
    já
    0.06
    ://${
    0.06
     Personali
    0.06
     reun
    0.06
    ummies
    0.06
    ä¹ħä¹ĭ
    0.06
     zet
    0.06
    ä¸įåħ¬
    0.06
    صار
    0.06
    Activations Density 0.028%

    No Known Activations