© 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. 54427
    Prev
    Next
    INDEX
    Explanations

    political contexts

    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
     localhost
    -0.26
    纣
    -0.26
    åıij
    -0.26
    å°±è¿ij
    -0.26
    rames
    -0.26
    çī¹åĪ«å£°æĺİ
    -0.25
    æĶ¾è¿Ľ
    -0.25
    ç«ĭ
    -0.25
    -addons
    -0.25
    »¿
    -0.24
    POSITIVE LOGITS
     state
    0.28
     indef
    0.26
     mass
    0.25
    çĩĶ
    0.25
     Mass
    0.25
     Dis
    0.25
     Und
    0.24
     def
    0.24
     Im
    0.24
     then
    0.24
    Activations Density 0.035%

    No Known Activations