© 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. 18-TRANSCODER-HP
    7. 89750
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    halb
    -0.28
    liest
    -0.27
     scrimmage
    -0.26
    bows
    -0.26
    rais
    -0.25
    lashes
    -0.25
    heiro
    -0.25
    èĢ·
    -0.25
    æ°©
    -0.24
    çĦĵ
    -0.24
    POSITIVE LOGITS
    åįļè§Ī
    0.27
    åĦ¿ç«¥
    0.26
     Contemporary
    0.25
    inc
    0.24
     Modern
    0.24
    çĪ¶
    0.24
     inject
    0.23
     Children
    0.23
    äºĭåĬ¡
    0.23
    inst
    0.23
    Activations Density 1.275%

    No Known Activations