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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 123049
    Prev
    Next
    INDEX
    Explanations

    om

    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
    规模
    -0.08
    asmine
    -0.08
    along
    -0.07
     الاستث
    -0.07
    ”。↵↵
    -0.07
    _IR
    -0.07
    ango
    -0.07
     paul
    -0.07
    蘼
    -0.07
     ni
    -0.07
    POSITIVE LOGITS
     multicultural
    0.08
    ::::::
    0.07
    .Content
    0.07
    .Mutex
    0.07
     lhs
    0.07
    msgid
    0.07
     presentation
    0.07
     Recommendation
    0.07
    )])
    0.07
    ises
    0.07
    Activations Density 0.001%

    No Known Activations