© 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. 12-TRANSCODER-HP
    7. 23085
    Prev
    Next
    INDEX
    Explanations

    Months and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     signaled
    -0.26
    çĥŁ
    -0.25
     Known
    -0.25
    hospital
    -0.25
    sm
    -0.25
    ä¸Ģç»Ħ
    -0.25
    ä¹ĭ家
    -0.24
    hem
    -0.24
    Hospital
    -0.24
    suit
    -0.24
    POSITIVE LOGITS
    UpDown
    0.28
    rawl
    0.27
    太平æ´ĭ
    0.25
    wik
    0.25
    thy
    0.25
     attr
    0.24
    å¼¥
    0.24
    头åıij
    0.24
     Lucy
    0.24
     Pratt
    0.24
    Activations Density 0.001%

    No Known Activations