© 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. 20-TRANSCODER-HP
    7. 106942
    Prev
    Next
    INDEX
    Explanations

    simplicity and difficulty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rium
    -0.29
    ñe
    -0.27
    protect
    -0.27
    AGER
    -0.26
    Protect
    -0.26
    éºĴ
    -0.25
     Eck
    -0.24
    owell
    -0.24
    èļķ
    -0.24
    ool
    -0.24
    POSITIVE LOGITS
    åı£åij³
    0.27
    dire
    0.26
    arding
    0.24
    è¡£
    0.24
    çĪª
    0.24
    ık
    0.24
    ×ķ×IJר
    0.24
     flask
    0.23
    åıĻè¿°
    0.23
     zwar
    0.23
    Activations Density 58.186%

    No Known Activations