© 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. 22658
    Prev
    Next
    INDEX
    Explanations

    arrival, about to happen

    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
    ustr
    -0.27
    »¿
    -0.26
    ĻĤ
    -0.26
    _DGRAM
    -0.26
    岫
    -0.25
    çIJ¬
    -0.25
     blurred
    -0.24
    /gl
    -0.24
    öt
    -0.24
    usters
    -0.23
    POSITIVE LOGITS
    pee
    0.30
    åĵį
    0.27
    èļ¤
    0.26
    èĥ½å¾ĹåĪ°
    0.25
    cee
    0.25
    ahoo
    0.25
    hole
    0.24
    ä¸ĩæĪ·
    0.24
    aci
    0.24
    çIJĨåıij
    0.24
    Activations Density 0.002%

    No Known Activations