© 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. 24-TRANSCODER-HP
    7. 150476
    Prev
    Next
    INDEX
    Explanations

    hom

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forth
    -0.31
    çĶ¨æĪ·æıIJä¾Ľ
    -0.27
    -mouth
    -0.27
    客æĪ·æıIJä¾Ľ
    -0.26
     aba
    -0.25
    å¿¿
    -0.24
     hang
    -0.24
     absol
    -0.24
    çĶ±ä¸ŃåĽ½
    -0.23
     hung
    -0.23
    POSITIVE LOGITS
    d
    0.32
    n
    0.30
    ses
    0.29
    l
    0.27
     Ñģобой
    0.27
    si
    0.26
    de
    0.26
    ipers
    0.25
    ucer
    0.25
    nel
    0.25
    Activations Density 1.356%

    No Known Activations