© 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. 27-TRANSCODER-HP
    7. 56690
    Prev
    Next
    INDEX
    Explanations

    Second-hand smoke/items

    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
    åħijçİ°
    -0.27
    Playing
    -0.25
    _playing
    -0.25
    quiv
    -0.25
    Pending
    -0.24
    åĬ¡å®ŀ
    -0.24
     setVisible
    -0.24
    poster
    -0.24
    razier
    -0.24
    icient
    -0.23
    POSITIVE LOGITS
     steer
    0.27
     Conf
    0.25
     mari
    0.25
     steam
    0.25
    ObjectContext
    0.24
    -flag
    0.24
    .dd
    0.24
    è¡Ŀ
    0.24
    =id
    0.24
    RuntimeObject
    0.24
    Activations Density 0.009%

    No Known Activations