© 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. 96575
    Prev
    Next
    INDEX
    Explanations

    Technical/medical documentation and news

    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
    routing
    -0.28
     taxation
    -0.27
    ledge
    -0.26
     Abdullah
    -0.25
    igin
    -0.25
    ç»Ļ大家
    -0.25
     stacking
    -0.24
    istani
    -0.24
    Indented
    -0.24
    -blocking
    -0.24
    POSITIVE LOGITS
    Recently
    0.36
     Recently
    0.33
     recently
    0.32
    Ñīа
    0.28
    ä¼ļå±ķ
    0.28
    å±ħ
    0.27
    æľĢè¿ij
    0.27
     ConnectionState
    0.26
    close
    0.26
    been
    0.26
    Activations Density 0.102%

    No Known Activations