© 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. 33-TRANSCODER-HP
    7. 52497
    Prev
    Next
    INDEX
    Explanations

    's

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ÑĥÑģÑĤ
    -0.29
    åĸĤ
    -0.27
     <<<
    -0.26
    ois
    -0.26
    itte
    -0.25
    icont
    -0.24
    uste
    -0.24
    Æ°ng
    -0.23
    feed
    -0.23
    lock
    -0.23
    POSITIVE LOGITS
    å¿ĥè¡Ģ
    0.27
     Hornets
    0.26
    ivor
    0.24
    æĻĸ
    0.24
     agent
    0.24
    æµ·åı£
    0.23
     agents
    0.23
    .species
    0.23
     PROC
    0.23
     ims
    0.23
    Activations Density 0.012%

    No Known Activations