© 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. 18-TRANSCODER-HP
    7. 89960
    Prev
    Next
    INDEX
    Explanations

    remarkably

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĭ¦
    -0.27
    第ä¸ī个
    -0.26
    èĬ¸
    -0.26
    (Profile
    -0.25
    ,"%
    -0.24
    Ve
    -0.24
    Åĭ
    -0.23
     "{{
    -0.23
    atedRoute
    -0.23
    _cli
    -0.23
    POSITIVE LOGITS
    è¿ĻäºĽä¸ľè¥¿
    0.29
     pile
    0.26
    elib
    0.25
    å½ĵåĪĿ
    0.25
    _stub
    0.25
    owns
    0.25
    versions
    0.24
    çij±
    0.24
    plate
    0.24
    .asm
    0.24
    Activations Density 1.571%

    No Known Activations