© 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. 27-TRANSCODER-HP
    7. 56833
    Prev
    Next
    INDEX
    Explanations

    How

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç»
    -0.28
    icamente
    -0.28
    depend
    -0.25
    adamente
    -0.25
    entered
    -0.25
     independently
    -0.25
    theless
    -0.24
    fully
    -0.24
     Entered
    -0.24
    们
    -0.24
    POSITIVE LOGITS
    ardy
    0.27
    istory
    0.25
    strom
    0.24
    åºĶ该å¦Ĥä½ķ
    0.24
    .onResume
    0.24
    åħĭæľį
    0.24
    å¦Ĥä½ķ
    0.24
    excel
    0.24
     overcoming
    0.23
     WHY
    0.23
    Activations Density 0.021%

    No Known Activations