© 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. 149703
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ç´¢åıĸ
    -0.28
    éĹ®ä»ĸ
    -0.28
    ç²Ĺ
    -0.28
    ç«ĭ项
    -0.27
    æĢı
    -0.27
    -hit
    -0.26
    çĸı
    -0.25
    PCM
    -0.25
    /MIT
    -0.25
    .Features
    -0.25
    POSITIVE LOGITS
     rejuven
    0.27
     ranging
    0.26
    éĶ»çĤ¼
    0.25
    âĪŁ
    0.25
     rotational
    0.25
    æİī
    0.25
    Cases
    0.25
    çĺ¦èº«
    0.25
    交
    0.24
    第ä¸ĢçĻ¾
    0.24
    Activations Density 0.251%

    No Known Activations

    This feature has no known activations.