© 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. 43884
    Prev
    Next
    INDEX
    Explanations

    Failures and alterations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä»ĬçĶŁ
    -0.29
     reserve
    -0.27
    igr
    -0.27
     Provided
    -0.25
    rac
    -0.25
    é©°
    -0.25
     commission
    -0.25
    .par
    -0.24
    åĨįéĢł
    -0.24
    andon
    -0.24
    POSITIVE LOGITS
     over
    0.36
     exploded
    0.29
    çī¹æ´¾
    0.29
    è¿ĩ
    0.28
     collapsed
    0.28
     hardened
    0.28
     unlocked
    0.27
    便
    0.27
     escalated
    0.27
     satisfied
    0.27
    Activations Density 0.002%

    No Known Activations