© 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. 25-TRANSCODER-HP
    7. 108273
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¾Ŀæ³ķ追究
    -0.26
    ScreenState
    -0.25
     Di
    -0.25
    ResponseType
    -0.25
    rimon
    -0.25
     Cynthia
    -0.24
    Di
    -0.24
    Fluid
    -0.24
    untime
    -0.24
    cctor
    -0.24
    POSITIVE LOGITS
    åĩ¡
    0.26
    å¹³åĿĩæ¯ı
    0.25
    -begin
    0.25
    è·Ŀ
    0.25
    anteed
    0.24
    .fast
    0.24
     forgetting
    0.23
    tie
    0.23
    æĪij说
    0.23
     memor
    0.23
    Activations Density 0.966%

    No Known Activations

    This feature has no known activations.