© 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. 25181
    Prev
    Next
    INDEX
    Explanations

    questions

    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
    etto
    -0.30
    arna
    -0.30
    anco
    -0.27
     anecd
    -0.26
    è¿Ļæł·
    -0.26
    å§ĭç»Ī
    -0.26
    ivement
    -0.24
     winner
    -0.24
    ató
    -0.24
    å½ĵæŶçļĦ
    -0.24
    POSITIVE LOGITS
    rary
    0.29
    иÑĤеÑģÑĮ
    0.24
     Diamonds
    0.24
     Params
    0.23
    çIJĥåľº
    0.22
     largo
    0.22
     Balls
    0.22
    éĤªæģ¶
    0.22
    libraries
    0.22
    <pre
    0.22
    Activations Density 0.000%

    No Known Activations