© 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
    2. Qwen3-4B
    3. 32-TRANSCODER-HP
    4. 41568
    Prev
    Next
    INDEX
    Explanations

    Seth

    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
    utan
    -0.28
    ä¸įæİĴéϤ
    -0.26
    cesso
    -0.26
    ften
    -0.25
    翳
    -0.25
    纨
    -0.24
    ä¸Ģå±Ĥ
    -0.24
     volatile
    -0.24
    客è§Ĥ
    -0.24
     Al
    -0.24
    POSITIVE LOGITS
    igham
    0.28
    emos
    0.27
    éĵ
    0.27
    éĿł
    0.27
    igram
    0.26
    numeric
    0.26
    çĶŁäº§æĢ»
    0.25
     Mellon
    0.25
    Scalars
    0.24
    ë´ī
    0.24
    Activations Density 0.001%

    No Known Activations