© 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. 12-TRANSCODER-HP
    7. 23539
    Prev
    Next
    INDEX
    Explanations

    9/11 and Al-Qaeda

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -League
    -0.29
    ĮĢ
    -0.27
     Newman
    -0.26
    è¶ĭ
    -0.26
    agus
    -0.26
    ahn
    -0.25
    è²Ĥ
    -0.25
     uncon
    -0.24
    agas
    -0.24
    opsis
    -0.24
    POSITIVE LOGITS
    æĻ®
    0.28
    isting
    0.26
     perman
    0.26
    atab
    0.25
    acl
    0.24
    ews
    0.24
     destined
    0.24
     landmarks
    0.23
     harms
    0.23
    te
    0.23
    Activations Density 0.002%

    No Known Activations