© 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. 19068
    Prev
    Next
    INDEX
    Explanations

    words ending in -ation or -ity

    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
    vs
    -0.07
    ret
    -0.06
    was
    -0.05
    and
    -0.05
    ÑĨев
    -0.05
    âĺ
    -0.05
    athe
    -0.05
    sem
    -0.05
    utte
    -0.05
    goto
    -0.05
    POSITIVE LOGITS
     sterling
    0.07
    anen
    0.06
    orge
    0.06
    icker
    0.06
    iramente
    0.06
    less
    0.06
     torn
    0.06
    åIJijè®°èĢħ
    0.06
    accio
    0.06
     Grosso
    0.06
    Activations Density 0.015%

    No Known Activations