© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 39733
    Prev
    Next
    INDEX
    Explanations

    Places/names with "heim"/"enheim"

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Madagascar
    -0.07
    希望大家
    -0.07
     Northern
    -0.07
    אח
    -0.07
    _FRIEND
    -0.07
     seasoned
    -0.07
    .readyState
    -0.07
    autoload
    -0.07
    <?↵
    -0.07
     emperor
    -0.07
    POSITIVE LOGITS
     publicly
    0.08
    VARCHAR
    0.07
    没错
    0.07
    .matmul
    0.07
    揍
    0.07
     cycl
    0.07
    ציין
    0.07
     gunshot
    0.07
    頻道
    0.07
    뱉
    0.07
    Activations Density 0.002%

    No Known Activations