© 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. 32-TRANSCODER-HP
    7. 42989
    Prev
    Next
    INDEX
    Explanations

    Software and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩĬæĶ¾
    -1.32
     release
    -1.26
    release
    -1.21
     Release
    -1.19
     releases
    -1.19
     releasing
    -1.15
    Release
    -1.13
     released
    -1.08
    -release
    -1.05
    _release
    -1.03
    POSITIVE LOGITS
    åĴĤ
    0.25
     set
    0.25
    éĶ»çĤ¼
    0.24
    æĭĶ
    0.24
    igin
    0.23
     cuts
    0.23
     Denis
    0.23
     Tet
    0.23
     bulbs
    0.23
    VEST
    0.23
    Activations Density 0.004%

    No Known Activations