© 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. 108528
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
    tons
    -0.27
    asto
    -0.27
    acute
    -0.26
    æ¢Ĺ
    -0.25
    ject
    -0.25
    -opt
    -0.24
    bao
    -0.24
    aste
    -0.24
    äºļåĨĽ
    -0.24
    èı½
    -0.24
    POSITIVE LOGITS
    欢è¿İæĤ¨
    0.33
    强度
    0.30
    寡
    0.28
     пÑĢоÑĤив
    0.28
    å´ĸ
    0.28
    vsp
    0.28
    æĪĺèĥľ
    0.28
    对æīĭ
    0.28
     rivalry
    0.27
    éģĩåĪ°äºĨ
    0.27
    Activations Density 2.301%

    No Known Activations