© 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. 106938
    Prev
    Next
    INDEX
    Explanations

    Questions and technical documentation

    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
     concessions
    -0.35
    åĢ¾
    -0.26
     concession
    -0.25
     Conservatives
    -0.25
     chancellor
    -0.25
    /***/
    -0.24
     bluff
    -0.24
    ầy
    -0.24
    -cons
    -0.24
     pacing
    -0.24
    POSITIVE LOGITS
    isan
    0.32
     TY
    0.28
    ello
    0.28
    ContentView
    0.28
    åįıåIJĮåıijå±ķ
    0.27
    عÙĪÙĨ
    0.27
    anager
    0.26
     listItem
    0.25
    éŨåºĹ
    0.24
    eve
    0.24
    Activations Density 3.442%

    No Known Activations