© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41075
    Prev
    Next
    INDEX
    Explanations

    state

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tle
    -0.26
    èĦ
    -0.25
    ALTH
    -0.25
    urb
    -0.25
    åī¯åİ¿éķ¿
    -0.25
    é¦
    -0.24
    IZER
    -0.24
     Commissioner
    -0.24
     Peer
    -0.24
    ORB
    -0.24
    POSITIVE LOGITS
    -states
    0.31
    -state
    0.30
     state
    0.29
     states
    0.29
    _boot
    0.27
     STATE
    0.26
    states
    0.25
    state
    0.25
    -State
    0.25
    -boot
    0.24
    Activations Density 0.000%

    No Known Activations