© 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. 88722
    Prev
    Next
    INDEX
    Explanations

    Random text snippets

    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
    jes
    -0.27
    Ñĥ
    -0.26
    aina
    -0.26
    arine
    -0.25
     Arrival
    -0.24
    elper
    -0.24
     arrived
    -0.24
    çĮľæµĭ
    -0.24
    碰
    -0.24
     wast
    -0.24
    POSITIVE LOGITS
    ä¸ĭæīĭ
    0.30
    _sol
    0.27
    ä¸īæĿ¡
    0.26
    -strokes
    0.25
    maint
    0.24
    ledger
    0.24
    (sw
    0.24
     Amendments
    0.24
    Indented
    0.24
    åĶIJ
    0.24
    Activations Density 4.215%

    No Known Activations