© 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. 53938
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    mma
    -0.30
    å¾Ĺèµ·
    -0.27
    uger
    -0.26
    zen
    -0.25
    åĪĨæķ£
    -0.25
    yclopedia
    -0.24
    -age
    -0.24
     clarity
    -0.24
    桧
    -0.24
    说å¾Ĺ
    -0.23
    POSITIVE LOGITS
    ato
    0.27
    aso
    0.27
    å±Ĥ
    0.26
     incons
    0.26
    æĬĦ
    0.25
     CHE
    0.25
    欸
    0.24
    еÑģÑĤв
    0.24
    çĽ¸ä¿¡å¤§å®¶
    0.24
    hatt
    0.24
    Activations Density 0.007%

    No Known Activations