© 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. 23698
    Prev
    Next
    INDEX
    Explanations

    radiation therapy

    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
    elly
    -0.27
    enticator
    -0.26
    éĻįä½İæĪIJæľ¬
    -0.25
    ç¡Į
    -0.25
    extr
    -0.25
    ìĶ¨
    -0.25
    çijĻ
    -0.25
    ideos
    -0.25
    grave
    -0.24
     Nep
    -0.24
    POSITIVE LOGITS
    è¿Ļè¾¹
    0.28
    éļ¾
    0.26
     half
    0.26
    æī©åħħ
    0.26
    dic
    0.26
    åħĪ
    0.25
    åįĬ
    0.24
    chor
    0.24
    å®ļåĪ¶
    0.24
    CTION
    0.24
    Activations Density 0.001%

    No Known Activations