© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54145
    Prev
    Next
    INDEX
    Explanations

    Text snippets and information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     present
    -0.44
    present
    -0.42
     Present
    -0.41
    Present
    -0.39
    nel
    -0.34
    _present
    -0.34
    çİ°
    -0.34
     presente
    -0.31
    -present
    -0.29
     présent
    -0.28
    POSITIVE LOGITS
    ØŃاÙĦ
    0.29
     cons
    0.27
     houses
    0.26
    house
    0.25
     Right
    0.25
     boarded
    0.25
    åºĬä¸Ĭ
    0.24
    .dex
    0.24
    cai
    0.24
     right
    0.24
    Activations Density 0.015%

    No Known Activations