© 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. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53332
    Prev
    Next
    INDEX
    Explanations

    Political activism context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     po
    -0.28
    ãĥĹãĥ©ãĤ¤
    -0.28
    PU
    -0.27
    iode
    -0.26
    åıij
    -0.26
    ikal
    -0.26
    æĪijä»¬çŁ¥éģĵ
    -0.25
     mil
    -0.25
    por
    -0.25
    åĴĮ个人
    -0.25
    POSITIVE LOGITS
     Scrolls
    0.27
     Tunnel
    0.26
    æŃ»èĢħ
    0.25
    é¼ł
    0.25
     лиÑĨа
    0.25
    liwo
    0.25
     uh
    0.24
    çĸı
    0.24
    _ATT
    0.24
     franca
    0.24
    Activations Density 0.024%

    No Known Activations