© 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. 24-TRANSCODER-HP
    7. 150133
    Prev
    Next
    INDEX
    Explanations

    Code using "require"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çŀ°
    -0.27
    ancies
    -0.27
    ç¬ijäºĨ
    -0.25
    fast
    -0.24
    anz
    -0.24
    à¨ľ
    -0.24
    ays
    -0.23
    celand
    -0.23
    对æĪijæĿ¥è¯´
    -0.23
    aylor
    -0.23
    POSITIVE LOGITS
    åĪĩ
    0.28
    chan
    0.27
    交éĢļ
    0.26
    traffic
    0.26
    osos
    0.25
    ifen
    0.25
    etSocketAddress
    0.25
    åIJĪä½ľåįıè®®
    0.25
    è®¤çŁ¥
    0.24
    交éĢļå®īåħ¨
    0.24
    Activations Density 0.904%

    No Known Activations