© 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. 27-TRANSCODER-HP
    7. 57035
    Prev
    Next
    INDEX
    Explanations

    academic texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĥæĺŁ
    -0.27
    åħ¨æ°ij
    -0.27
    amientos
    -0.27
    commons
    -0.26
    éĢģåĪ°
    -0.25
    å½±
    -0.25
    Âł↵
    -0.24
    æĥ³åĪ°
    -0.24
    å®ŀåľ¨æĺ¯
    -0.24
    .TextImageRelation
    -0.24
    POSITIVE LOGITS
     elucid
    0.28
    診
    0.28
    .obs
    0.25
    ucid
    0.25
    RLF
    0.25
    次
    0.24
    assi
    0.24
     cyl
    0.24
     reports
    0.24
    assin
    0.24
    Activations Density 0.322%

    No Known Activations