© 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. 43802
    Prev
    Next
    INDEX
    Explanations

    random data/code snippets

    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
    defs
    -0.29
    è½»
    -0.28
    pus
    -0.24
    issing
    -0.24
    avit
    -0.24
     prim
    -0.24
     immediate
    -0.24
    æ½¢
    -0.24
     virgin
    -0.23
     Immediate
    -0.23
    POSITIVE LOGITS
    空æ°Ķ
    0.30
    空æ°Ķè´¨éĩı
    0.27
     obe
    0.25
    .air
    0.25
    LLU
    0.25
    parer
    0.24
    acf
    0.24
    agram
    0.24
    PMC
    0.24
    空æ°Ķä¸Ń
    0.24
    Activations Density 0.001%

    No Known Activations