© 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. 18-TRANSCODER-HP
    7. 89668
    Prev
    Next
    INDEX
    Explanations

    doc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uss
    -0.28
    -issue
    -0.26
     Rate
    -0.25
    æĶ¿
    -0.25
    çİĩè¾¾
    -0.24
    -production
    -0.24
    çİĩè¾¾åĪ°
    -0.24
     animation
    -0.24
    resents
    -0.24
     correl
    -0.24
    POSITIVE LOGITS
    身ä½ĵåģ¥åº·
    0.26
    çĶŁæ´»çļĦ
    0.26
    ROY
    0.25
    å¹´ä¹ĭ
    0.24
    bourg
    0.24
    .kind
    0.24
    parity
    0.24
    æĪijè¿ĺæĺ¯
    0.23
    ipline
    0.23
    imon
    0.23
    Activations Density 1.226%

    No Known Activations