© 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. 18-TRANSCODER-HP
    7. 89836
    Prev
    Next
    INDEX
    Explanations

    exile/deportation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Plenty
    -0.28
    earch
    -0.28
    stroy
    -0.26
    ç¶ļ
    -0.26
    åħħåĪĨåĪ©çĶ¨
    -0.26
    toDouble
    -0.25
    elts
    -0.25
    draulic
    -0.25
     Giles
    -0.25
    pageTitle
    -0.25
    POSITIVE LOGITS
    us
    0.27
    æĮĩ导æĦıè§ģ
    0.26
     Femin
    0.25
    amo
    0.25
    =set
    0.24
    åĩºåľº
    0.24
    ç¾Ķ
    0.24
     Already
    0.24
     оÑĤмеÑĤ
    0.23
    oral
    0.23
    Activations Density 15.433%

    No Known Activations