© 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. 19-RESID-POST-AA
    11. 89432
    Prev
    Next
    INDEX
    Explanations

    Relating to others

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ','.
    -0.07
    (Collider
    -0.07
    splash
    -0.06
    Saint
    -0.06
     devuelve
    -0.06
     '/',↵
    -0.06
    ᑯ
    -0.06
    Environment
    -0.06
     Pinterest
    -0.06
    .design
    -0.06
    POSITIVE LOGITS
    nels
    0.07
     Yüksek
    0.07
    ráf
    0.07
    aset
    0.07
    会影响
    0.07
    路
    0.07
     keyPressed
    0.07
    iek
    0.07
    总决赛
    0.06
    monds
    0.06
    Activations Density 0.057%

    No Known Activations