© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21881
    Prev
    Next
    INDEX
    Explanations

    terms of endearment or family terms

    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
    ichern
    -0.07
    lander
    -0.07
    hoff
    -0.07
    é¦ĻçļĦ
    -0.06
    lands
    -0.06
    rach
    -0.06
    ваÑĩ
    -0.06
    unner
    -0.06
    hani
    -0.06
    arach
    -0.06
    POSITIVE LOGITS
    [:,:
    0.05
    ation
    0.05
    åĨł
    0.05
    ve
    0.05
    zn
    0.05
    sson
    0.05
    ('_',
    0.05
    vely
    0.05
     kidding
    0.05
    çģ¶
    0.05
    Activations Density 0.001%

    No Known Activations