© 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. 22240
    Prev
    Next
    INDEX
    Explanations

    respiratory and cough related illnesses

    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
    ment
    -0.06
    berger
    -0.06
    upal
    -0.06
    ä¸įæŃ»
    -0.05
     exhaustion
    -0.05
    èĪĶ
    -0.05
    vester
    -0.05
    stress
    -0.05
    NR
    -0.05
    IRC
    -0.05
    POSITIVE LOGITS
    ilup
    0.06
    orca
    0.05
     íı
    0.05
    å½±åĵį
    0.05
     دک
    0.05
    thought
    0.05
    atura
    0.05
    itano
    0.05
    好çļĦ产åĵģ
    0.05
    olica
    0.05
    Activations Density 0.001%

    No Known Activations