© 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. 16950
    Prev
    Next
    INDEX
    Explanations

    halogen or pseudohalogen chemistry

    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
    ed
    -0.07
    urio
    -0.07
    -grade
    -0.07
    erschaft
    -0.07
    emps
    -0.06
    otros
    -0.06
    ánchez
    -0.06
    imentary
    -0.06
    ×ķ×¢
    -0.06
    è´¹çŃī
    -0.06
    POSITIVE LOGITS
    azing
    0.06
     obvious
    0.06
    декваÑĤ
    0.05
    artial
    0.05
    çIJĨæĻº
    0.05
    schn
    0.05
    idget
    0.05
    çĦ¶æĺ¯
    0.05
     Entr
    0.05
    天çļĦ
    0.05
    Activations Density 0.006%

    No Known Activations