© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96919
    Prev
    Next
    INDEX
    Explanations

    scientific measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     {
    -0.55
    {
    -0.50
    {i
    -0.48
    {x
    -0.47
    {n
    -0.46
    ï½Ľ
    -0.45
    {(
    -0.44
    {k
    -0.43
     {(
    -0.42
    {l
    -0.40
    POSITIVE LOGITS
     with
    1.33
    with
    1.19
     With
    1.07
    With
    1.03
    _with
    1.02
    	with
    1.01
     avec
    0.99
     vỼi
    0.98
     dengan
    0.98
    .with
    0.93
    Activations Density 0.929%

    No Known Activations