© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98052
    Prev
    Next
    INDEX
    Explanations

    software context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     full
    -0.28
    Full
    -0.28
     star
    -0.27
    umu
    -0.26
    :num
    -0.26
     Full
    -0.26
     All
    -0.25
    star
    -0.25
    -scripts
    -0.25
    Script
    -0.24
    POSITIVE LOGITS
     ..."↵↵
    0.28
    çı°
    0.27
    alone
    0.27
    olist
    0.25
    gesch
    0.25
     flo
    0.25
    LEE
    0.25
     Paulo
    0.24
    fell
    0.24
    åĶ§
    0.24
    Activations Density 0.000%

    No Known Activations