© 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. 41577
    Prev
    Next
    INDEX
    Explanations

    crafting and decoration

    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
    esity
    -0.28
    ylim
    -0.27
     physical
    -0.26
    åıĮåIJij
    -0.26
     immunity
    -0.25
    lim
    -0.25
     precipitation
    -0.25
     Prec
    -0.25
     exposition
    -0.24
    ç½ij绾ç§ijæĬĢ
    -0.24
    POSITIVE LOGITS
    cent
    0.30
     pigs
    0.29
     accents
    0.28
    -sw
    0.26
    çĮª
    0.25
    äºĶæĺŁ
    0.25
     shoes
    0.25
    ç®´
    0.25
    baar
    0.24
     Michaels
    0.24
    Activations Density 0.012%

    No Known Activations