© 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. 25170
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
     nós
    -0.26
     definitely
    -0.25
     sen
    -0.25
    Ctrls
    -0.25
     specific
    -0.25
     nous
    -0.25
    ichel
    -0.25
     particular
    -0.25
     me
    -0.24
     shop
    -0.24
    POSITIVE LOGITS
     Sherman
    0.27
    educt
    0.26
    resher
    0.26
     visions
    0.26
    lan
    0.25
    æĮĩåįĹ
    0.24
    alu
    0.24
    ;'>
    0.24
     Trom
    0.24
    иÑģк
    0.24
    Activations Density 0.014%

    No Known Activations