© 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. 24124
    Prev
    Next
    INDEX
    Explanations

    Web article segments

    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
     mat
    -0.28
     oran
    -0.28
     \%
    -0.26
    ç¥ĿæĦ¿
    -0.26
    tems
    -0.25
     chees
    -0.25
    ObjectContext
    -0.25
    tons
    -0.24
    _hooks
    -0.24
    mat
    -0.23
    POSITIVE LOGITS
     Instruction
    0.28
     Vikings
    0.27
    FW
    0.25
    ghan
    0.25
    çĵ¯
    0.24
     Dialogue
    0.24
     Episode
    0.24
    VF
    0.24
    visual
    0.23
    .swift
    0.23
    Activations Density 0.030%

    No Known Activations