© 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. 9569
    Prev
    Next
    INDEX
    Explanations

    device

    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
     opciones
    -0.07
     jihadist
    -0.07
    уще
    -0.06
     którego
    -0.06
    가는
    -0.06
     durch
    -0.06
    㳘
    -0.06
     Durch
    -0.06
     stimulation
    -0.06
    _READONLY
    -0.06
    POSITIVE LOGITS
    用自己的
    0.07
     Recreation
    0.07
    不代表
    0.07
    .initializeApp
    0.07
    工程项目
    0.07
     defaultCenter
    0.07
    DateTime
    0.07
    ById
    0.07
    ánt
    0.07
    #$
    0.07
    Activations Density 0.002%

    No Known Activations