© 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. 30-TRANSCODER-HP
    7. 96027
    Prev
    Next
    INDEX
    Explanations

    atmosphere

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Accred
    -0.27
     lite
    -0.27
    lite
    -0.26
     ramps
    -0.25
    icum
    -0.25
    nees
    -0.25
     Action
    -0.25
     batching
    -0.25
    upo
    -0.24
    $action
    -0.24
    POSITIVE LOGITS
    åį°
    0.33
     composed
    0.32
    æ´ĭ
    0.30
    -o
    0.29
    æ·±
    0.27
     caused
    0.26
     consisting
    0.26
     oceans
    0.26
    OSP
    0.26
    åį°ç«ł
    0.25
    Activations Density 0.014%

    No Known Activations