© 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. 107807
    Prev
    Next
    INDEX
    Explanations

    tired

    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
    èĭ¦
    -0.29
    fur
    -0.27
    顽强
    -0.24
    sects
    -0.24
    å½¼
    -0.24
    èIJĺ
    -0.24
     handset
    -0.24
    ulis
    -0.23
    äºļè¿IJä¼ļ
    -0.23
    ibbon
    -0.23
    POSITIVE LOGITS
     dimension
    0.29
    ctor
    0.27
     Amen
    0.26
     infer
    0.25
    rot
    0.24
    çŀ¢
    0.24
     ignorant
    0.24
     stem
    0.24
     grasp
    0.24
     Ded
    0.24
    Activations Density 0.906%

    No Known Activations