© 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. 90313
    Prev
    Next
    INDEX
    Explanations

    sensors and detection

    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
     pedest
    -0.26
    é¼ĵ
    -0.25
    udit
    -0.25
     platinum
    -0.25
    udio
    -0.24
    ä¹Łä¸º
    -0.23
    .authorization
    -0.23
     Platinum
    -0.23
     transcript
    -0.23
    outing
    -0.23
    POSITIVE LOGITS
    ulet
    0.32
    éĻ¤
    0.29
    ulas
    0.29
     ÑıзÑĭк
    0.28
    LF
    0.27
    ãģ°ãģĭãĤĬ
    0.26
    rip
    0.25
    rite
    0.24
     ÑģÑĤеп
    0.24
     güç
    0.23
    Activations Density 24.345%

    No Known Activations