© 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. 150384
    Prev
    Next
    INDEX
    Explanations

    first time experiences

    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
    é¦ĸ次
    -1.09
    第ä¸Ģ次
    -0.95
    åĪĿãĤģãģ¦
    -0.79
    åĪĿ次
    -0.66
    пеÑĢв
    -0.65
     unprecedented
    -0.59
    åīįæīĢæľªæľī
    -0.56
    åīįæīĢæľª
    -0.53
    第äºĮ次
    -0.50
    第ä¸ī次
    -0.49
    POSITIVE LOGITS
    ä¸įæĸŃ
    0.28
    ivec
    0.26
    åħĪ
    0.25
    缸çĪ±
    0.25
    éķ¿å¤§
    0.24
    ä¸įæĸ·
    0.24
    trace
    0.24
    KeyType
    0.23
    ä¸į好
    0.23
    ä¸įæĸŃçļĦ
    0.23
    Activations Density 0.993%

    No Known Activations