© 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. 30-TRANSCODER-HP
    7. 95602
    Prev
    Next
    INDEX
    Explanations

    afflicted, damaged

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pistol
    -0.33
    TOT
    -0.30
    -cur
    -0.29
    åIJĪ
    -0.26
    æł¼
    -0.25
    oref
    -0.25
    idine
    -0.24
     kut
    -0.24
     Pty
    -0.24
     Neg
    -0.24
    POSITIVE LOGITS
     affected
    0.47
    affected
    0.41
    åıĹå½±åĵį
    0.39
     cause
    0.36
     afflicted
    0.35
    åıĹæįŁ
    0.33
     damaged
    0.33
     impacted
    0.32
     causes
    0.30
     injured
    0.29
    Activations Density 0.889%

    No Known Activations