© 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. 22-TRANSCODER-HP
    7. 87589
    Prev
    Next
    INDEX
    Explanations

    beauty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aders
    -0.27
    ifle
    -0.26
    .crm
    -0.26
    _dispatch
    -0.24
    iquement
    -0.24
    enties
    -0.23
    èµ°åİ»
    -0.23
    ifest
    -0.23
    å£ij
    -0.23
    让æĤ¨
    -0.22
    POSITIVE LOGITS
     vs
    0.39
     versus
    0.38
    ä¸İ
    0.36
    vsp
    0.32
     âĨĶ
    0.31
    vs
    0.30
     <->
    0.30
    _vs
    0.29
    èĪĩ
    0.28
     alongside
    0.28
    Activations Density 0.005%

    No Known Activations