© 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. 12-TRANSCODER-HP
    7. 23926
    Prev
    Next
    INDEX
    Explanations

    radiation and particle errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odge
    -0.26
    ymoon
    -0.26
    ouri
    -0.26
    uya
    -0.25
    ivan
    -0.25
    iday
    -0.24
    Configurer
    -0.24
    .cgi
    -0.24
    lang
    -0.23
    URY
    -0.23
    POSITIVE LOGITS
    flags
    0.30
     flags
    0.30
    æĹĹ
    0.27
    da
    0.26
     chall
    0.25
    -flag
    0.25
    aN
    0.25
    Flags
    0.24
     dn
    0.24
     flag
    0.24
    Activations Density 0.001%

    No Known Activations