© 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. 22-TRANSCODER-HP
    7. 97708
    Prev
    Next
    INDEX
    Explanations

    titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÅĦst
    -0.27
    edException
    -0.25
    reste
    -0.25
    ä½ľåĵģåĨħ容
    -0.25
    akra
    -0.24
    [table
    -0.24
    pcm
    -0.24
    nj
    -0.24
    _NB
    -0.24
    ndon
    -0.24
    POSITIVE LOGITS
     ожи
    0.28
    注æĺİåĩºå¤Ħ
    0.27
    Aug
    0.26
    çĿĽ
    0.25
    çŀİ
    0.24
    è¿ĻåĿĹ
    0.24
    aug
    0.24
     says
    0.24
    uity
    0.24
     Aug
    0.24
    Activations Density 0.007%

    No Known Activations