© 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. 150700
    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
    spe
    -0.24
    ]*(
    -0.24
     shutil
    -0.23
    оÑģÑĮ
    -0.23
    eed
    -0.23
     suitcase
    -0.23
    {(
    -0.23
    ny
    -0.23
     disap
    -0.23
    ä¹Įé²ģ
    -0.23
    POSITIVE LOGITS
    айн
    0.27
    åıįå¤į
    0.25
    cripts
    0.24
     Ged
    0.24
    amel
    0.24
    éķŃ
    0.24
     rou
    0.24
    Las
    0.23
    æ¿Ģåħī
    0.23
    æ¯ıä¸Ģä½į
    0.23
    Activations Density 1.202%

    No Known Activations

    This feature has no known activations.