© 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. 20-TRANSCODER-HP
    7. 130242
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getPlayer
    -0.26
    ’T
    -0.26
    æł¡
    -0.25
    egas
    -0.25
    "default
    -0.24
    á»ij
    -0.24
    ’ét
    -0.24
    å¨ĥå¨ĥ
    -0.24
    çľĭæ¸ħ
    -0.24
    <AM
    -0.23
    POSITIVE LOGITS
     Rew
    0.26
     sur
    0.25
    åij½
    0.25
    rew
    0.24
     treated
    0.24
    onga
    0.24
     agenda
    0.24
     part
    0.23
    olo
    0.23
    (.)
    0.23
    Activations Density 0.957%

    No Known Activations