© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 111214
    Prev
    Next
    INDEX
    Explanations

    ylan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DIFF
    -0.08
    眬
    -0.08
    uspendLayout
    -0.07
    _TRIANGLE
    -0.07
    Fill
    -0.07
     bóng
    -0.07
    .findall
    -0.07
    ตรง
    -0.07
     Align
    -0.07
     Leaves
    -0.07
    POSITIVE LOGITS
     Bowman
    0.07
     además
    0.07
     Hak
    0.07
     expended
    0.07
    عص
    0.06
    (blocks
    0.06
    hg
    0.06
     [|
    0.06
     bard
    0.06
     abolish
    0.06
    Activations Density 0.027%

    No Known Activations