© 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. 25-TRANSCODER-HP
    7. 107851
    Prev
    Next
    INDEX
    Explanations

    binary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LR
    -0.28
    å®ı
    -0.26
    onaut
    -0.26
    aises
    -0.25
    ONUS
    -0.24
    macro
    -0.23
     Seiten
    -0.23
     migrations
    -0.23
    aptop
    -0.23
    Curr
    -0.23
    POSITIVE LOGITS
    æĺ¯åĽłä¸º
    0.30
    zie
    0.29
    è¿Ļç§įæĥħåĨµ
    0.28
    è¿Ļç§įæĸ¹å¼ı
    0.27
    igo
    0.27
    åİŁåĽł
    0.25
    æĺ¯æĪij们
    0.24
    zier
    0.24
    è¿Ļæĺ¯åĽłä¸º
    0.24
     responsible
    0.24
    Activations Density 0.016%

    No Known Activations