© 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. 24024
    Prev
    Next
    INDEX
    Explanations

    Code/technical writing

    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
     interviewer
    -0.29
    --+
    -0.28
    æѧè§Ĩ
    -0.27
    éĥ¾
    -0.26
     Vaults
    -0.26
    åĬłåĪĨ
    -0.25
    /operators
    -0.25
    è°ĥåīĤ
    -0.25
     vibrator
    -0.24
    ÙĪض
    -0.24
    POSITIVE LOGITS
     processed
    0.27
    ¤í
    0.27
     degraded
    0.26
    processed
    0.26
     mature
    0.26
    xis
    0.26
    Principal
    0.25
    -bodied
    0.24
    ÑĨий
    0.24
    åĬ£
    0.24
    Activations Density 0.007%

    No Known Activations