© 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. 108211
    Prev
    Next
    INDEX
    Explanations

    Code and text snippets

    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
    onomy
    -0.27
    myp
    -0.27
    AndPassword
    -0.26
     crest
    -0.25
     submerged
    -0.24
    çļĦåĬ¨åĬĽ
    -0.24
    åij¨ä¸ī
    -0.24
    /tool
    -0.24
    ony
    -0.24
    æĶ¶è´¹æłĩåĩĨ
    -0.24
    POSITIVE LOGITS
    çķĮ第ä¸Ģ
    0.30
     identical
    0.27
    pered
    0.27
    izon
    0.25
     separate
    0.25
     ÑģÑĢазÑĥ
    0.25
     second
    0.25
    iones
    0.24
    éĩį
    0.24
    第äºĮ
    0.24
    Activations Density 0.895%

    No Known Activations