© 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. 20177
    Prev
    Next
    INDEX
    Explanations

    seconds, minutes, floors, license

    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
    erma
    -0.08
    Ïīνα
    -0.07
    mals
    -0.07
    elius
    -0.07
    ymax
    -0.06
    Playable
    -0.06
    äºĶéĩij交çĶµ
    -0.06
    ÑģÑĭпа
    -0.06
    olare
    -0.06
    ttl
    -0.06
    POSITIVE LOGITS
    伯
    0.06
    (
    0.06
     h
    0.05
    e
    0.05
    AT
    0.05
     f
    0.05
    ern
    0.05
    beh
    0.05
    ez
    0.05
    "
    0.05
    Activations Density 0.006%

    No Known Activations