© 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. 96177
    Prev
    Next
    INDEX
    Explanations

    is

    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
     subject
    -1.84
    subject
    -1.55
     Subject
    -1.45
    Subject
    -1.41
    .subject
    -1.25
     subjects
    -1.24
    (subject
    -1.20
     SUBJECT
    -1.20
    _subject
    -1.20
    _SUBJECT
    -1.09
    POSITIVE LOGITS
    dialogs
    0.25
    åºĨåħ¸
    0.25
     Jord
    0.25
     Moms
    0.25
    leton
    0.24
    unist
    0.24
    루
    0.23
    ilation
    0.23
    çģ¶
    0.23
    çķ´
    0.23
    Activations Density 0.919%

    No Known Activations