© 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. 19198
    Prev
    Next
    INDEX
    Explanations

    chloride or chloric acid

    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
    Ø´Ùħ
    -0.08
    roduk
    -0.08
    zcze
    -0.08
    pons
    -0.08
    Einst
    -0.08
    WITHOUT
    -0.07
    åŁĶ寨
    -0.07
    ullah
    -0.07
    stwo
    -0.07
    Envelope
    -0.07
    POSITIVE LOGITS
    0.07
    er
    0.07
    ex
    0.07
    Âł
    0.07
    /
    0.06
    ↵
    0.06
    !
    0.06
    ↵↵
    0.06
    ,
    0.06
     (
    0.05
    Activations Density 0.001%

    No Known Activations