© 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. 19298
    Prev
    Next
    INDEX
    Explanations

    famous, controversial, mysterious, anticipated, dreaded, awaited

    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
    æ´ŀ
    -0.05
    Âł
    -0.05
    -0.04
    çī¹
    -0.04
    çĶŁ
    -0.04
    å±ĭ
    -0.04
     accordingly
    -0.04
    rip
    -0.04
    éĩĬ
    -0.04
     rep
    -0.04
    POSITIVE LOGITS
    hil
    0.07
    heits
    0.07
    intang
    0.07
    vrouw
    0.07
    utori
    0.07
    ancier
    0.06
    hone
    0.06
    ĥģ
    0.06
    延年
    0.06
    actors
    0.06
    Activations Density 0.150%

    No Known Activations