© 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. 95432
    Prev
    Next
    INDEX
    Explanations

    book reviews and excerpts

    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
    ENCED
    -0.30
     jails
    -0.29
    çİ©
    -0.28
     scripted
    -0.27
    æĪª
    -0.26
     Sens
    -0.26
    éļ¾
    -0.26
     Alert
    -0.25
     alert
    -0.25
     mol
    -0.24
    POSITIVE LOGITS
    oodle
    0.29
    _TUN
    0.28
    unter
    0.27
    anford
    0.26
     unfavor
    0.26
    èĩªå®¶
    0.25
     optim
    0.25
    cdnjs
    0.24
    favorite
    0.24
    æĿ¥çĶµ
    0.24
    Activations Density 0.887%

    No Known Activations