© 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. 88947
    Prev
    Next
    INDEX
    Explanations

    Drug names

    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
    Kn
    -0.33
    ste
    -0.28
    Observ
    -0.28
    kn
    -0.27
    éĻ¤å¤ĸ
    -0.27
    Ste
    -0.27
    FB
    -0.27
    ÑģÑĤал
    -0.25
    NG
    -0.25
     Observ
    -0.25
    POSITIVE LOGITS
     motor
    0.27
    idelity
    0.27
    motor
    0.26
    tright
    0.26
    ltra
    0.26
    nia
    0.26
    ppy
    0.26
     converged
    0.25
    ertext
    0.25
    rosse
    0.25
    Activations Density 3.480%

    No Known Activations