© 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. 54055
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     group
    -0.84
     Group
    -0.81
     groups
    -0.76
     Groups
    -0.74
    Group
    -0.73
    -group
    -0.72
     GROUP
    -0.71
    group
    -0.70
     groupId
    -0.69
    _group
    -0.66
    POSITIVE LOGITS
     gr
    0.67
    gr
    0.62
    -gr
    0.57
    .gr
    0.56
     Gr
    0.55
    (gr
    0.54
    _gr
    0.54
    Gr
    0.52
    	gr
    0.51
    .Gr
    0.46
    Activations Density 0.040%

    No Known Activations