© 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. 12-TRANSCODER-HP
    7. 23512
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pulver
    -0.27
    åıijå±ķéĺ¶æ®µ
    -0.25
    lightbox
    -0.25
    åħ³éĶ®æŶåĪ»
    -0.25
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.24
    arLayout
    -0.24
    ä»ĸåıĪ
    -0.24
     nr
    -0.23
     cotton
    -0.23
    æįIJçĮ®
    -0.23
    POSITIVE LOGITS
    æ´Ĺ
    0.28
     reins
    0.27
     phil
    0.26
    opia
    0.26
    oha
    0.26
    TION
    0.26
    éĩįçİ°
    0.25
     comic
    0.25
    éĿ©
    0.25
    aside
    0.24
    Activations Density 0.004%

    No Known Activations