© 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. 33-TRANSCODER-HP
    7. 53135
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     liner
    -0.26
    ENU
    -0.26
    ovi
    -0.26
    代çIJĨ
    -0.26
    agement
    -0.25
    bd
    -0.25
     DU
    -0.25
     slots
    -0.25
    orno
    -0.24
    iltr
    -0.24
    POSITIVE LOGITS
     ideal
    1.70
    çIJĨæĥ³
    1.66
     Ideal
    1.52
    çIJĨæĥ³çļĦ
    1.45
    ideal
    1.43
    çļĦçIJĨæĥ³
    1.42
    Ideal
    1.39
     ideals
    0.89
     ideally
    0.81
     иде
    0.70
    Activations Density 0.109%

    No Known Activations