© 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. 18092
    Prev
    Next
    INDEX
    Explanations

    not working or failing

    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
    estra
    -0.06
    ood
    -0.06
    ä¹Ī
    -0.05
     Rowe
    -0.05
    ond
    -0.05
    ogan
    -0.05
    ee
    -0.05
    plex
    -0.05
    aw
    -0.05
    à·Ĵනà·Ĭ
    -0.05
    POSITIVE LOGITS
    éĶ¦æ¶Ľ
    0.06
    ij¸
    0.06
    upakan
    0.06
     seguint
    0.06
    eszcze
    0.05
    igny
    0.05
     reflect
    0.05
     Element
    0.05
    cara
    0.05
    ingers
    0.05
    Activations Density 0.100%

    No Known Activations