© 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. 23123
    Prev
    Next
    INDEX
    Explanations

    Truncated/incomplete texts

    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
     Copp
    -0.28
    ä¸į解
    -0.27
     flag
    -0.27
     peek
    -0.26
    Ctx
    -0.25
    åħ¨
    -0.25
    颡
    -0.25
     Äijô
    -0.25
    >{@
    -0.25
     Flag
    -0.24
    POSITIVE LOGITS
    æĸ°ä¸ī
    0.28
    ä¾¿å®ľ
    0.28
    ients
    0.25
    chio
    0.25
    év
    0.24
    第ä¸ĢçĻ¾
    0.24
    \Validator
    0.24
    为èĩªå·±
    0.24
    phalt
    0.24
     Shepard
    0.24
    Activations Density 0.001%

    No Known Activations