© 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. 41491
    Prev
    Next
    INDEX
    Explanations

    estimating group sizes

    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
    è¿ij
    -0.29
    å¥¹åľ¨
    -0.28
    ordinate
    -0.27
    让她
    -0.27
    acons
    -0.26
    ilen
    -0.26
    chip
    -0.26
    -License
    -0.26
    eil
    -0.26
    她
    -0.25
    POSITIVE LOGITS
     evacuated
    0.26
     tw
    0.26
     Words
    0.26
    &R
    0.26
    Words
    0.25
     another
    0.24
    ä¹Ŀåįģ
    0.24
    çĮĸ
    0.24
    åıĤè°ĭ
    0.24
     further
    0.24
    Activations Density 0.002%

    No Known Activations