© 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. 23-TRANSCODER-HP
    7. 24426
    Prev
    Next
    INDEX
    Explanations

    corporation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ±çĶŁ
    -0.27
    otify
    -0.27
    æĹıèĩªæ²»åİ¿
    -0.25
    çİ«çij°
    -0.25
    大å¸Ī
    -0.24
    apore
    -0.24
     pitched
    -0.23
    ')+
    -0.23
    å¸Ńåį·
    -0.23
    емÑģÑı
    -0.23
    POSITIVE LOGITS
     <![
    0.28
     tightly
    0.26
     closely
    0.26
    æĥ³ä¸įåĪ°
    0.26
    jud
    0.26
     captive
    0.25
     dictionaries
    0.25
    -parameter
    0.25
     medic
    0.24
    æµħ
    0.24
    Activations Density 0.001%

    No Known Activations