© 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. 24-TRANSCODER-HP
    7. 150857
    Prev
    Next
    INDEX
    Explanations

    life experiences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Imports
    -0.40
     imports
    -0.37
     IMPORT
    -0.36
    -*-
    -0.33
    import
    -0.33
     import
    -0.33
    uses
    -0.30
    #!/
    -0.29
    #include
    -0.29
    	import
    -0.28
    POSITIVE LOGITS
    使å¾Ĺ
    0.42
    使
    0.38
    éĢłæĪIJäºĨ
    0.38
    带æĿ¥äºĨ
    0.35
    åĬ©éķ¿
    0.33
    让æĤ¨
    0.33
    ä¿ĥè¿ĽäºĨ
    0.31
    带æĿ¥
    0.31
    ä¿ĥ使
    0.31
    çķĻä¸ĭäºĨ
    0.31
    Activations Density 1.025%

    No Known Activations