© 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. 42948
    Prev
    Next
    INDEX
    Explanations

    iron

    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
     pv
    -0.29
    CHA
    -0.27
    dio
    -0.27
    arias
    -0.26
    é¡·
    -0.26
    æīĢ产çĶŁçļĦ
    -0.26
     Slug
    -0.26
    秽
    -0.25
    ITH
    -0.25
    лок
    -0.25
    POSITIVE LOGITS
    umas
    0.29
    agar
    0.26
    umb
    0.26
    âĢij
    0.25
    æ³ķå®ļ
    0.25
     íĥ
    0.25
    кажеÑĤ
    0.24
     inflater
    0.24
     Randolph
    0.24
    ä¼łå¯¼
    0.23
    Activations Density 0.001%

    No Known Activations