© 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. 22526
    Prev
    Next
    INDEX
    Explanations

    scientific and technical descriptions

    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
     Kendrick
    -0.27
    æ·±å±Ĥ次
    -0.26
    èĢĮéĿŀ
    -0.26
    çĥĽ
    -0.25
     next
    -0.25
    esk
    -0.25
     greens
    -0.25
    keley
    -0.24
    ¶ļ
    -0.24
    继ç»Ń
    -0.23
    POSITIVE LOGITS
    Clone
    0.28
     Clone
    0.28
    PLE
    0.27
    ãĥĬãĥ«
    0.26
    ple
    0.25
    uble
    0.25
    DAQ
    0.24
    åıĭ
    0.24
    èģĥ
    0.24
     inf
    0.24
    Activations Density 0.003%

    No Known Activations