© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 109366
    Prev
    Next
    INDEX
    Explanations

    Code and technical documentation

    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
    Negative Logits
    ä¸Ģåī¯
    -0.33
    没è§ģè¿ĩ
    -0.28
    ä¸ĸçķĮçļĦ
    -0.28
    ynes
    -0.27
    é£İåħī
    -0.26
    æĹłæĦı
    -0.25
    榨
    -0.25
    itra
    -0.25
    åīįæīĢæľª
    -0.25
    Frameworks
    -0.25
    POSITIVE LOGITS
    onian
    0.29
    andon
    0.27
    SuccessListener
    0.26
    oyal
    0.26
    anner
    0.26
    ennon
    0.25
    erson
    0.24
    hire
    0.24
    'O
    0.24
    learner
    0.24
    Activations Density 0.893%

    No Known Activations