© 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. 151004
    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
    对æĸ¹
    -0.32
     labour
    -0.28
    å°įæĸ¹
    -0.28
    uren
    -0.26
    ijľ
    -0.25
    åľ¨æĪijçļĦ
    -0.25
    nod
    -0.24
    disposed
    -0.24
    ERY
    -0.24
    å°ıé¾Ļ
    -0.24
    POSITIVE LOGITS
    åĨĴ
    0.38
    mnt
    0.28
    pisa
    0.27
    表çİ°
    0.26
    amos
    0.25
    åºĶçĶ¨åľºæĻ¯
    0.24
     Lah
    0.23
    cust
    0.23
    亡
    0.23
    hait
    0.23
    Activations Density 0.892%

    No Known Activations

    This feature has no known activations.