© 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. 9-TRANSCODER-HP
    7. 29505
    Prev
    Next
    INDEX
    Explanations

    forget

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    纶
    -0.27
    个æĢ§
    -0.25
    inceton
    -0.25
     threshold
    -0.25
    书æĪ¿
    -0.24
    Pocket
    -0.24
    èīºæľ¯å®¶
    -0.24
    bac
    -0.24
     Spir
    -0.23
     Opport
    -0.23
    POSITIVE LOGITS
    anker
    0.29
    å±ħçĦ¶
    0.27
    вÑıз
    0.26
    oding
    0.26
    arme
    0.26
    oth
    0.26
    ç¥Ģ
    0.25
    åįĥåı¤
    0.25
    ory
    0.25
    anel
    0.24
    Activations Density 2.265%

    No Known Activations