© 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. 33-TRANSCODER-HP
    7. 54421
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åĵºä¹³
    -0.25
     systemic
    -0.25
    iesta
    -0.25
    веÑģÑĤ
    -0.25
     dél
    -0.24
    composition
    -0.24
    è°ķ
    -0.23
    æĪķ
    -0.23
    eneg
    -0.23
    üst
    -0.23
    POSITIVE LOGITS
    appoint
    0.28
    append
    0.27
    äºĮåįģåĽĽ
    0.26
    åıĭè°Ĭ
    0.26
     salty
    0.26
     append
    0.25
    -append
    0.25
    äºĶåĪĨéĴŁ
    0.25
     Presbyterian
    0.24
     {č↵č↵č↵
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.