© 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. 108748
    Prev
    Next
    INDEX
    Explanations

    code, references, bibliography

    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
    æłª
    -0.27
    注è§Ĩ
    -0.25
    å²ģæŶ
    -0.25
    STEM
    -0.25
    åĪ°åºķæĺ¯
    -0.24
    -drop
    -0.24
    åģ¥
    -0.24
    åĪ°åºķ
    -0.23
     Stem
    -0.23
     stem
    -0.23
    POSITIVE LOGITS
    ensch
    0.28
    åħļçļĦé¢Ĩ导
    0.27
    ennen
    0.26
    otal
    0.26
    uden
    0.26
    æķĪ
    0.25
    _IMETHOD
    0.25
     Radical
    0.25
    otify
    0.24
    _SHADOW
    0.24
    Activations Density 0.908%

    No Known Activations