© 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. 35-TRANSCODER-HP
    7. 39335
    Prev
    Next
    INDEX
    Explanations

    words with "self"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Virt
    -0.27
    wk
    -0.26
     part
    -0.25
    RON
    -0.25
    ä»Ģä¹Īåı«
    -0.24
    øy
    -0.24
    -part
    -0.23
     itself
    -0.23
    جÙĬ
    -0.23
    åģ¥åº·æĪIJéķ¿
    -0.23
    POSITIVE LOGITS
    æĦıæĥ³ä¸įåĪ°
    0.25
    åħµ
    0.25
    plemented
    0.25
    iate
    0.24
    ropri
    0.24
    aves
    0.24
    eeper
    0.24
    ades
    0.24
    aab
    0.24
    çİ°
    0.24
    Activations Density 2.466%

    No Known Activations