© 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. 27-TRANSCODER-HP
    7. 56862
    Prev
    Next
    INDEX
    Explanations

    programming syntax and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eler
    -0.29
    atto
    -0.27
    ainting
    -0.26
    ÃŃm
    -0.25
    Imports
    -0.25
     msm
    -0.24
    iram
    -0.24
    çļĦäºĭå®ŀ
    -0.24
    æij¸
    -0.24
     mmc
    -0.23
    POSITIVE LOGITS
    çĤ¹çĤ¹å¤´
    0.50
     nodded
    0.50
     nods
    0.48
    çĤ¹äºĨçĤ¹å¤´
    0.46
     nod
    0.45
    çĤ¹å¤´
    0.40
    =Y
    0.39
    åĹ¯
    0.36
    nod
    0.34
    {T
    0.31
    Activations Density 0.025%

    No Known Activations