© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163059
    Prev
    Next
    INDEX
    Explanations

    hunting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ej
    -0.28
     OE
    -0.26
    .annotations
    -0.24
    åīįåı°
    -0.24
     Washing
    -0.24
    åıĮè¾¹
    -0.24
    çĨ¨
    -0.24
    zej
    -0.24
     Entered
    -0.23
    OE
    -0.23
    POSITIVE LOGITS
    æĪIJ绩
    0.27
    çłį
    0.26
    imity
    0.26
    locked
    0.26
    oin
    0.25
    amy
    0.25
     lesb
    0.24
    sm
    0.24
    urious
    0.23
    ASET
    0.23
    Activations Density 0.643%

    No Known Activations