Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 7-TRANSCODER-HP
    4. 21786
    Prev
    Next
    INDEX
    Explanations

    radical, org

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vens
    -0.31
    裳
    -0.28
    äºĮ级
    -0.27
    çģŃçģ«
    -0.27
    åħ¬åħ±
    -0.26
    untu
    -0.25
    ä¾§
    -0.25
    reur
    -0.25
    mer
    -0.25
    lish
    -0.25
    POSITIVE LOGITS
     \↵↵
    0.26
    jual
    0.25
     owe
    0.25
    åĬłå¿«å»ºè®¾
    0.25
    NIL
    0.24
     profil
    0.23
    atology
    0.23
    ä¹ħäºĨ
    0.23
    å§Ķå±Ī
    0.23
     backstory
    0.23
    Activations Density 0.007%

    No Known Activations