© 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. 22646
    Prev
    Next
    INDEX
    Explanations

    computer-generated text

    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
    åĽŃ
    -0.30
    éĺ³åİ¿
    -0.28
     profile
    -0.28
    é¦Ĩ
    -0.27
     tum
    -0.25
    profile
    -0.25
    代çIJĨ
    -0.25
    -t
    -0.25
     prelim
    -0.25
    社
    -0.25
    POSITIVE LOGITS
    /cop
    0.26
    atif
    0.25
     Drill
    0.25
    çĥ¬
    0.25
    endon
    0.24
    icio
    0.24
    mbH
    0.24
     untranslated
    0.24
    èĢģåħ¬
    0.23
     oath
    0.23
    Activations Density 0.000%

    No Known Activations