© 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. 43365
    Prev
    Next
    INDEX
    Explanations

    a

    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
     sea
    -0.33
     Sea
    -0.32
    éĻĨ
    -0.32
    æµ·
    -0.32
     snow
    -0.31
     land
    -0.30
     clouds
    -0.30
     equ
    -0.30
    æĹĹ
    -0.30
    éĻ¸
    -0.30
    POSITIVE LOGITS
    段
    0.25
    hydro
    0.25
    emer
    0.25
    åı«
    0.25
    _hyper
    0.24
    临
    0.24
    ﻤ
    0.24
    iola
    0.24
    hy
    0.24
    Hen
    0.24
    Activations Density 0.004%

    No Known Activations