© 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. 109086
    Prev
    Next
    INDEX
    Explanations

    washing and brushing

    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
    åıĤ
    -0.26
    åĩ¹
    -0.26
    operands
    -0.26
    çĬ¹è±«
    -0.25
     operated
    -0.25
    elder
    -0.24
    æī§
    -0.24
    欲
    -0.24
     commerc
    -0.23
    符
    -0.23
    POSITIVE LOGITS
    orian
    0.28
    iore
    0.26
    åŀ¢
    0.25
    cis
    0.24
    heimer
    0.23
     mar
    0.23
    éĵ
    0.23
     kone
    0.23
    mar
    0.23
    .mar
    0.23
    Activations Density 0.163%

    No Known Activations