© 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. 32-TRANSCODER-HP
    7. 41767
    Prev
    Next
    INDEX
    Explanations

    cell types

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Buff
    -0.34
    ç¼ĵåĨ²
    -0.32
    Buffer
    -0.29
     BUFFER
    -0.29
     buff
    -0.28
     buffers
    -0.28
     Buffer
    -0.28
     buffer
    -0.28
    buffers
    -0.27
    BUFFER
    -0.27
    POSITIVE LOGITS
    zin
    0.28
     cell
    0.26
    ysis
    0.26
    综åIJĪåĪ©çĶ¨
    0.24
    veled
    0.24
    ovo
    0.24
    ä¸įæ¸ħ
    0.24
    ittal
    0.24
    FlowLayout
    0.24
    owl
    0.24
    Activations Density 0.005%

    No Known Activations