© 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. 54083
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act-logits · gemini-2.0-flash
    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
    \db
    -0.27
    é¢ĦçķĻ
    -0.26
    culos
    -0.26
    .converter
    -0.26
    _mass
    -0.25
    åĬ³
    -0.25
    amen
    -0.24
     preserved
    -0.24
    gó
    -0.24
    íĮĶ
    -0.24
    POSITIVE LOGITS
    lle
    0.29
    æį®æĬ¥éģĵ
    0.28
    åįĬæľĪ
    0.27
    .minute
    0.26
    abo
    0.25
    åıĤä¸İåĪ°
    0.25
    ä¸įæİĴéĻ¤
    0.25
    ãĤĤãĤĬ
    0.25
    èĪŀåı°
    0.25
     Parade
    0.24
    Activations Density 0.244%

    No Known Activations