© 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. 129647
    Prev
    Next
    INDEX
    Explanations

    Risks

    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
    pite
    -0.29
     throne
    -0.26
     Empire
    -0.26
     Throne
    -0.26
     gains
    -0.25
    æºī
    -0.25
    ä¸Ģè§Ĵ
    -0.24
    åĵ¿
    -0.24
    rique
    -0.23
     BRE
    -0.23
    POSITIVE LOGITS
    è·ijäºĨ
    0.27
    دة
    0.25
    IDEO
    0.25
    qed
    0.24
    <_
    0.23
     Depos
    0.23
    æŶéļĶ
    0.23
    .run
    0.23
    迷失
    0.23
    æ·³
    0.22
    Activations Density 9.096%

    No Known Activations