© 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. 17677
    Prev
    Next
    INDEX
    Explanations

    killing, death, shoot

    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
    HCI
    -0.06
    æijĨ
    -0.06
    enge
    -0.06
    åIJİæĤĶ
    -0.06
     rede
    -0.05
    oop
    -0.05
    åĤĻ
    -0.05
    uki
    -0.05
    çĶ¨éĢĶ
    -0.05
    endienst
    -0.05
    POSITIVE LOGITS
    æīĵæĸŃ
    0.06
     glas
    0.05
    åıŃ
    0.05
    netinet
    0.05
    æĸĩåĮĸèĬĤ
    0.05
    ¬ģ
    0.05
    åħįäºİ
    0.05
    erties
    0.05
    ä¸īçŃī
    0.05
    ert
    0.05
    Activations Density 0.001%

    No Known Activations