© 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. 18892
    Prev
    Next
    INDEX
    Explanations

    semi- prefixes

    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
    ãĤĪãģĨãģ«
    -0.07
    ongs
    -0.07
    forgettable
    -0.07
    an
    -0.07
    stras
    -0.07
    aná
    -0.06
    omad
    -0.06
    taki
    -0.06
    espo
    -0.06
    ease
    -0.06
    POSITIVE LOGITS
    ness
    0.06
    elen
    0.06
    son
    0.06
    offrir
    0.05
    ï¸ı
    0.05
    elaar
    0.05
    ities
    0.05
    éļĻ
    0.05
    effectuer
    0.05
    ence
    0.05
    Activations Density 0.022%

    No Known Activations