© 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. 89824
    Prev
    Next
    INDEX
    Explanations

    plants

    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
    iams
    -0.27
    Thrown
    -0.27
     lash
    -0.26
     interp
    -0.25
     Decay
    -0.25
     fort
    -0.25
     Walters
    -0.24
     Zimmer
    -0.24
    主è§Ĥ
    -0.24
    åĻİ
    -0.24
    POSITIVE LOGITS
    佩æľį
    0.25
     McDon
    0.25
    haar
    0.25
     shock
    0.23
    æĦ§
    0.23
    _HTML
    0.23
    oron
    0.23
    ä¸įåħį
    0.23
    MMC
    0.22
     Shock
    0.22
    Activations Density 4.415%

    No Known Activations