© 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. 23445
    Prev
    Next
    INDEX
    Explanations

    Arc

    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
    rzy
    -0.27
    çŁ³å®¶åºĦ
    -0.26
    affected
    -0.26
    igraph
    -0.26
     Mig
    -0.26
    çŁ³å®¶
    -0.26
    -lfs
    -0.25
    (Spring
    -0.25
    actly
    -0.25
    hone
    -0.24
    POSITIVE LOGITS
     Filipino
    0.35
     Philippine
    0.31
     Philippines
    0.29
    èı²å¾ĭ宾
    0.29
    BERS
    0.27
     nues
    0.26
    åIJĪ
    0.26
    éĺĻ
    0.26
    ãĥģãĥ¥
    0.25
     Manila
    0.25
    Activations Density 0.002%

    No Known Activations