© 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. 89919
    Prev
    Next
    INDEX
    Explanations

    Gas

    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
    ço
    -0.26
     unfolded
    -0.25
     am
    -0.25
     Che
    -0.25
     treating
    -0.25
     kadar
    -0.24
     Try
    -0.24
    oded
    -0.24
     Rhodes
    -0.24
    Try
    -0.24
    POSITIVE LOGITS
     sidel
    0.27
     DialogResult
    0.26
    è·³è·ĥ
    0.24
    anium
    0.24
     dew
    0.24
    åħįéĻ¤
    0.24
     comfortably
    0.23
    è´´
    0.23
    0.23
     Edu
    0.23
    Activations Density 6.085%

    No Known Activations