© 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. 149852
    Prev
    Next
    INDEX
    Explanations

    why

    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
    åł°
    -0.29
     sodom
    -0.29
    coder
    -0.26
    -mean
    -0.26
    ä¹ĭå¤ľ
    -0.26
    æĮĩ导ä¸ĭ
    -0.25
    GBT
    -0.25
    å¤ľéĩĮ
    -0.25
     FRE
    -0.25
    æ±
    -0.24
    POSITIVE LOGITS
     wet
    0.27
    èĴ»
    0.27
     contacts
    0.26
     scan
    0.26
    ctal
    0.26
     invert
    0.25
    ris
    0.25
     emit
    0.25
    ish
    0.24
     clean
    0.24
    Activations Density 0.198%

    No Known Activations