© 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. 95305
    Prev
    Next
    INDEX
    Explanations

    surveys and responses

    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
     answer
    -1.45
    åĽŀçŃĶ
    -1.45
    çŃĶ
    -1.45
    çŃĶæ¡Ī
    -1.30
     Answer
    -1.30
     answered
    -1.27
    Answer
    -1.26
     answers
    -1.26
     answering
    -1.25
    çļĦåĽŀçŃĶ
    -1.24
    POSITIVE LOGITS
    å´§
    0.26
    æĢĢæĬ±
    0.25
    uum
    0.25
    ainen
    0.25
    eload
    0.25
    åIJĥåĪ°
    0.24
    vented
    0.23
    CTIONS
    0.23
    æ»ĭåħ»
    0.23
    argo
    0.23
    Activations Density 0.896%

    No Known Activations