© 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. 108319
    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
    otropic
    -0.27
    imens
    -0.27
     canvas
    -0.26
    ipsis
    -0.25
    åıĮåıĮ
    -0.25
     sings
    -0.24
     enclosing
    -0.24
     vibr
    -0.24
    bis
    -0.23
     chữ
    -0.23
    POSITIVE LOGITS
     Dict
    0.25
     min
    0.25
     Reporter
    0.25
     responder
    0.25
     dictator
    0.24
    nees
    0.24
    æ´»çĿĢ
    0.24
    è¶Ĭå¤ļ
    0.24
    DER
    0.24
     traveller
    0.24
    Activations Density 0.123%

    No Known Activations

    This feature has no known activations.