© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40719
    Prev
    Next
    INDEX
    Explanations

    Slavic/Eastern European origin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     BoxFit
    -0.29
     hostage
    -0.26
     shrine
    -0.26
     ?>'
    -0.26
     prompting
    -0.25
     reminding
    -0.25
     hostages
    -0.25
    ä¸Ģ声
    -0.24
     '//
    -0.24
     timeouts
    -0.24
    POSITIVE LOGITS
     Cla
    0.30
    xia
    0.30
     Pam
    0.28
    zung
    0.28
    ted
    0.28
    IZER
    0.28
     Wald
    0.27
    缸è¾ĥ
    0.27
     zie
    0.27
    ÑĤÑĢа
    0.27
    Activations Density 0.052%

    No Known Activations