© 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. 54262
    Prev
    Next
    INDEX
    Explanations

    academic texts

    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
    æł¼
    -0.27
    åĴ¸
    -0.25
    FormatException
    -0.25
    ç»ĻåĬĽ
    -0.25
    rawer
    -0.25
     assim
    -0.25
    IVED
    -0.25
    ImageSharp
    -0.24
    ç»Ĺ
    -0.24
     enumer
    -0.24
    POSITIVE LOGITS
    åĨł
    0.30
    olv
    0.27
    isters
    0.25
    âĹĦ
    0.25
    æ°¸
    0.25
    onaut
    0.25
    å¤ļäºĨ
    0.25
    lands
    0.25
     Lamar
    0.24
    ays
    0.24
    Activations Density 0.022%

    No Known Activations