© 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. 33-TRANSCODER-HP
    7. 54450
    Prev
    Next
    INDEX
    Explanations

    flowing

    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
     lands
    -0.30
     land
    -0.30
     Lands
    -0.29
    irim
    -0.28
    lands
    -0.27
    æľº
    -0.27
    stad
    -0.25
    åħľ
    -0.25
    åİļ度
    -0.25
    vo
    -0.24
    POSITIVE LOGITS
     flowed
    0.30
    Flow
    0.27
    æĪIJå°±
    0.27
    achievement
    0.27
     flows
    0.27
     flow
    0.26
     Flow
    0.26
    FormField
    0.25
    achie
    0.24
    -flow
    0.24
    Activations Density 0.085%

    No Known Activations