© 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. 32-TRANSCODER-HP
    7. 42854
    Prev
    Next
    INDEX
    Explanations

    Code and database context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    turn
    -0.28
    çİĭåħĪçĶŁ
    -0.28
     turning
    -0.27
    closure
    -0.27
     material
    -0.27
    birth
    -0.26
    material
    -0.26
     seeking
    -0.26
    GO
    -0.25
    ohl
    -0.25
    POSITIVE LOGITS
     perform
    0.41
     performs
    0.40
     performed
    0.39
    perform
    0.39
     Perform
    0.38
    .perform
    0.38
    Perform
    0.35
     Performing
    0.31
    ละà¸Ħร
    0.30
    .Perform
    0.30
    Activations Density 0.001%

    No Known Activations