© 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. 25226
    Prev
    Next
    INDEX
    Explanations

    Facing challenges or aftermath

    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
    gran
    -0.29
    çĤĻ
    -0.29
    æģĭ人
    -0.27
    sbin
    -0.27
    éĻĦ
    -0.26
    æĹłå£°
    -0.26
    aml
    -0.25
    aaaa
    -0.25
    AG
    -0.25
    agic
    -0.24
    POSITIVE LOGITS
     Sit
    0.28
     concede
    0.27
     cont
    0.26
    Sit
    0.26
    ellig
    0.25
     ...↵↵↵↵
    0.25
     situ
    0.25
     situations
    0.25
     scrimmage
    0.24
     signals
    0.24
    Activations Density 0.034%

    No Known Activations