© 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. 23307
    Prev
    Next
    INDEX
    Explanations

    Split words

    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
     \|
    -0.26
    çĥĪ
    -0.25
    åŁİéĻħ
    -0.24
    etest
    -0.24
    alse
    -0.24
     Dw
    -0.24
    aneously
    -0.24
    .ef
    -0.24
    éĻįå¹ħ
    -0.24
    ise
    -0.23
    POSITIVE LOGITS
    åĽ´
    0.33
     persu
    0.28
     Ñĥме
    0.27
    rape
    0.26
    éĩįä¸Ń
    0.26
     Weeks
    0.26
    wrapped
    0.25
    Wrap
    0.25
    åĬłçıŃ
    0.24
    æĶ¾å®½
    0.24
    Activations Density 0.001%

    No Known Activations