© 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. 32-TRANSCODER-HP
    7. 42713
    Prev
    Next
    INDEX
    Explanations

    chemical and medical processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ansa
    -0.34
    lington
    -0.27
     Aid
    -0.25
    å´¤
    -0.24
    æīįå¹²
    -0.24
    lok
    -0.24
     orbital
    -0.24
     вал
    -0.24
    æ²»
    -0.24
    俸
    -0.24
    POSITIVE LOGITS
    -Sep
    0.33
    ured
    0.30
    -pro
    0.28
    uring
    0.26
    verted
    0.26
     MEP
    0.26
    leys
    0.26
    upert
    0.26
     struggles
    0.25
    å¼ı
    0.25
    Activations Density 0.001%

    No Known Activations