© 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. 20186
    Prev
    Next
    INDEX
    Explanations

    assassination, abortion, killed, car bombs

    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
    åĬ«
    -0.06
    è¯Ĩ
    -0.06
    pron
    -0.06
    ÏĦοÏį
    -0.06
     */)
    -0.06
    emm
    -0.06
     اÙĦØ°Ùĩب
    -0.06
    èŃĺ
    -0.06
     conject
    -0.06
     aud
    -0.06
    POSITIVE LOGITS
    ilon
    0.06
    太éĥİ
    0.05
     kus
    0.05
    åıĺ缸
    0.05
     port
    0.05
    arate
    0.05
    éļıåľ°
    0.05
     Hatch
    0.05
    drawable
    0.04
    åħļåĨħ
    0.04
    Activations Density 0.005%

    No Known Activations