© 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. 149619
    Prev
    Next
    INDEX
    Explanations

    religious/spiritual texts

    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
     itself
    -0.27
    åħ±äº§
    -0.27
    èĩªèº«
    -0.27
     ltd
    -0.25
    ={({
    -0.25
     autop
    -0.25
    nip
    -0.25
     MPL
    -0.24
    ä¸Ģ页
    -0.24
     coup
    -0.24
    POSITIVE LOGITS
    æĪij们
    0.29
    åĴ±ä»¬
    0.27
    illis
    0.26
    笺
    0.26
    elon
    0.26
    æĪij们就
    0.26
     Salv
    0.25
     us
    0.25
    为æĪij们
    0.25
    çļĦåºĶçĶ¨
    0.24
    Activations Density 0.134%

    No Known Activations