© 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. 108196
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    np_max-act-logits · gemini-2.0-flash
    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
     BaseController
    -0.28
    written
    -0.28
     CLOSED
    -0.26
    guide
    -0.25
     incor
    -0.25
    craft
    -0.25
    åĺĺ
    -0.25
     Placeholder
    -0.24
     Connector
    -0.24
    ANTLR
    -0.24
    POSITIVE LOGITS
    åı£
    0.29
    è¾¾
    0.28
    zens
    0.28
    æĤĶ
    0.27
    çī©
    0.27
    oundation
    0.26
    è¯ģåĪ¸
    0.25
    lim
    0.25
    Ag
    0.24
    utf
    0.24
    Activations Density 0.235%

    No Known Activations