© 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. 20763
    Prev
    Next
    INDEX
    Explanations

    game, story, unique, review

    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
    ax
    -0.05
     ant
    -0.05
    aid
    -0.05
     plausible
    -0.05
    .
    -0.04
    ↵↵
    -0.04
    apo
    -0.04
     applied
    -0.04
     R
    -0.04
    udy
    -0.04
    POSITIVE LOGITS
     Webs
    0.08
    adres
    0.07
    åı«
    0.06
    åħĨ
    0.06
    åĪ°å°¾
    0.06
     Trilogy
    0.06
    éĢ¼
    0.06
     relentlessly
    0.06
     vir
    0.06
    idu
    0.06
    Activations Density 0.004%

    No Known Activations