© 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. 24-TRANSCODER-HP
    7. 150241
    Prev
    Next
    INDEX
    Explanations

    Code, errors, and foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quina
    -0.27
    æĸ°ä¸ī
    -0.27
    UNS
    -0.26
    è¸ı
    -0.26
    _war
    -0.25
    æĺŁçº§
    -0.25
    ega
    -0.25
    åıĮåIJij
    -0.25
     Simmons
    -0.24
    庶
    -0.24
    POSITIVE LOGITS
    æµ·è¾¹
    0.27
    ç¿¡
    0.26
    icip
    0.26
    çĪ±ç¾İ
    0.25
    principal
    0.25
    _altern
    0.25
    Mir
    0.24
    æĨĶ
    0.24
    sched
    0.24
     Chore
    0.24
    Activations Density 0.010%

    No Known Activations