© 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. 23-TRANSCODER-HP
    7. 24777
    Prev
    Next
    INDEX
    Explanations

    unlock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sacrific
    -0.28
    å½»
    -0.28
    adic
    -0.25
    jaw
    -0.25
    bus
    -0.25
    Ñĩив
    -0.25
    éĻ¢éķ¿
    -0.25
    è¿ĩ
    -0.24
    ãģķãĤĮãĤĭãģĵãģ¨
    -0.24
     algu
    -0.24
    POSITIVE LOGITS
     prim
    0.28
     hidden
    0.25
     distance
    0.25
     imp
    0.25
     movement
    0.25
     commission
    0.25
     flipped
    0.24
     Ax
    0.24
     marginal
    0.24
     prime
    0.24
    Activations Density 0.006%

    No Known Activations