© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41128
    Prev
    Next
    INDEX
    Explanations

    various text

    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
    avit
    -0.29
    8
    -0.29
    æ¿Ģ
    -0.28
    ages
    -0.28
    èĮļ
    -0.27
    åħ«ä¸ª
    -0.26
     eight
    -0.25
     League
    -0.25
    -eight
    -0.25
    erten
    -0.25
    POSITIVE LOGITS
    aylor
    0.26
    çĸ¼
    0.26
    icode
    0.26
    æĴĻ
    0.26
    çģ¶
    0.26
    大äºĭ
    0.25
    .Enter
    0.24
    etration
    0.24
    大çĪ·
    0.23
    esh
    0.23
    Activations Density 0.005%

    No Known Activations