© 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. 35-TRANSCODER-HP
    7. 39311
    Prev
    Next
    INDEX
    Explanations

    simulation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eno
    -0.28
    ifo
    -0.28
    roit
    -0.26
    å®ł
    -0.26
     "()
    -0.26
    ir
    -0.25
    isto
    -0.25
    ponse
    -0.25
     Stoke
    -0.25
    ÑģÑĤолÑĮ
    -0.25
    POSITIVE LOGITS
    模æĭŁ
    0.39
     simulate
    0.39
     simulation
    0.38
    simulate
    0.38
    Simulation
    0.38
    simulation
    0.36
     simulations
    0.35
     simulated
    0.35
     Simulation
    0.34
    _simulation
    0.33
    Activations Density 0.016%

    No Known Activations