© 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. 90111
    Prev
    Next
    INDEX
    Explanations

    technical issues

    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
    Negative Logits
     attempt
    -0.35
     attempted
    -0.34
    curity
    -0.33
     Attempt
    -0.32
     attempts
    -0.32
     Attempts
    -0.31
     attempting
    -0.30
    åı«
    -0.27
    pery
    -0.27
    tempts
    -0.26
    POSITIVE LOGITS
    nist
    0.29
    xing
    0.28
    /storage
    0.28
    ä½ľåĵģåĨħ容
    0.25
    nw
    0.24
    éķŃ
    0.24
    æ§ĥ
    0.24
    peace
    0.24
    æĪijæīį
    0.23
    å°¼åħĭ
    0.23
    Activations Density 39.141%

    No Known Activations