© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 58335
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cul
    -0.27
     Key
    -0.26
    CU
    -0.25
    åĨ³å®ļ
    -0.24
     dequeue
    -0.24
    åħ¨éĥ¨
    -0.24
    使çĶ¨çļĦ
    -0.24
    ä»Ģä¹Īåľ°æĸ¹
    -0.24
    egr
    -0.24
    çļĦæĸĩç«ł
    -0.23
    POSITIVE LOGITS
    ÃŃf
    0.27
    ç´¯äºĨ
    0.26
    ä¸įè¿ľ
    0.25
    滥
    0.25
    Extras
    0.25
    geries
    0.24
    extras
    0.24
    èĮĥåĨ°åĨ°
    0.24
    arella
    0.24
    @dynamic
    0.24
    Activations Density 0.000%

    No Known Activations