© 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. 22214
    Prev
    Next
    INDEX
    Explanations

    content types

    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
    åł
    -0.06
    çĹķ
    -0.06
    еÑĢбÑĥ
    -0.06
    ause
    -0.06
    onna
    -0.05
    íĺ¸
    -0.05
    petto
    -0.05
    ä¾ĿéĿł
    -0.05
     thirst
    -0.05
    é¥Ńç¢Ĺ
    -0.05
    POSITIVE LOGITS
     matching
    0.06
    è§ģæѤ
    0.06
    ÙģÙĦ
    0.06
     corresp
    0.06
     accordingly
    0.06
    åĮ¹éħį
    0.05
    dam
    0.05
     natur
    0.05
     qualifiers
    0.05
     matches
    0.05
    Activations Density 0.081%

    No Known Activations