© 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. 52872
    Prev
    Next
    INDEX
    Explanations

    al

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åİĭåĬĽ
    -0.28
    ળ
    -0.27
    æĢľ
    -0.27
    çļĦåİĭåĬĽ
    -0.27
     structured
    -0.27
     architecture
    -0.26
    殿
    -0.26
    ilden
    -0.25
    LING
    -0.25
     Architecture
    -0.25
    POSITIVE LOGITS
     por
    0.28
    por
    0.28
    ountry
    0.27
    éĽ¢ãĤĮ
    0.26
    icles
    0.26
    åįĬ
    0.26
    -out
    0.26
    out
    0.25
    åĬ¨
    0.25
    å§Ķ
    0.24
    Activations Density 0.022%

    No Known Activations