© 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. 12-TRANSCODER-HP
    7. 22745
    Prev
    Next
    INDEX
    Explanations

    letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thirsty
    -0.27
    -ren
    -0.26
    mente
    -0.24
    fé
    -0.24
    åħ¼
    -0.24
    bote
    -0.24
    踱
    -0.24
    åħ³èĬĤ
    -0.24
    ört
    -0.24
     CFR
    -0.23
    POSITIVE LOGITS
    éķ¿æ²Ļ
    0.26
    åıī
    0.26
    atto
    0.26
    icum
    0.25
    éķ¿æ²Ļå¸Ĥ
    0.25
    uct
    0.24
     nowhere
    0.24
    ripper
    0.24
    éŀį
    0.24
    apan
    0.24
    Activations Density 0.010%

    No Known Activations