© 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. 88491
    Prev
    Next
    INDEX
    Explanations

    while

    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
    nte
    -0.28
    åĽºçĦ¶
    -0.28
    èĻ½çĦ¶
    -0.27
    neas
    -0.26
     zwar
    -0.25
     Reflex
    -0.25
    asz
    -0.25
     JAXBElement
    -0.24
     zza
    -0.23
    çķ¶çĦ¶
    -0.23
    POSITIVE LOGITS
    panic
    0.27
    hei
    0.26
    iesen
    0.25
     faces
    0.25
    äºĭåħĪ
    0.24
    ESIS
    0.24
    sys
    0.24
     secured
    0.24
    çķ¸
    0.24
     heavily
    0.23
    Activations Density 15.234%

    No Known Activations