© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18757
    Prev
    Next
    INDEX
    Explanations

    data frame structure

    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
    agio
    -0.05
    ible
    -0.05
    ãģ§
    -0.05
    (?:
    -0.05
    ishing
    -0.05
    amani
    -0.05
    iro
    -0.05
    ↵↵    ↵
    -0.05
    _mag
    -0.05
    %",
    -0.05
    POSITIVE LOGITS
    edom
    0.06
    hz
    0.06
    itari
    0.06
     urmÄĥ
    0.06
    upd
    0.06
    çĪ±ä¸į
    0.06
    /her
    0.05
    hint
    0.05
    dou
    0.05
    Marks
    0.05
    Activations Density 0.001%

    No Known Activations