© 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. 12-TRANSCODER-HP
    7. 23537
    Prev
    Next
    INDEX
    Explanations

    Code and legal text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ificance
    -0.27
    驳
    -0.26
    HLT
    -0.26
    -fi
    -0.26
    æįº
    -0.25
    embers
    -0.25
    uctose
    -0.25
    ughters
    -0.24
    plode
    -0.24
    olph
    -0.24
    POSITIVE LOGITS
    lix
    0.29
    åĽ´
    0.28
    nea
    0.28
     Starting
    0.28
     starting
    0.27
    Starting
    0.26
     sortOrder
    0.25
     convenience
    0.25
     Coil
    0.25
     ListItem
    0.24
    Activations Density 0.001%

    No Known Activations