© 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. 20-TRANSCODER-HP
    7. 63922
    Prev
    Next
    INDEX
    Explanations

    threat

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ucer
    -0.32
    çī¹å®ļ
    -0.29
    å¯Ĩ
    -0.29
    没è§ģè¿ĩ
    -0.27
    夹
    -0.26
    æ¸ħæĻ°
    -0.26
    æ²ŁéĢļ
    -0.26
     quem
    -0.25
    å°ıæŶåĨħ
    -0.25
    atomy
    -0.25
    POSITIVE LOGITS
    Tap
    0.31
     Hamp
    0.31
    зав
    0.28
     wrought
    0.26
     Tap
    0.25
    zÄħ
    0.25
    sein
    0.25
    outu
    0.25
    åĮª
    0.23
    ç»ŀ
    0.23
    Activations Density 15.868%

    No Known Activations