© 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. 11-RESID-POST-AA
    11. 75967
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     оформ
    -0.08
    쿵
    -0.07
    שק
    -0.07
    老乡
    -0.07
     위원님
    -0.06
     majestic
    -0.06
     ihtiyaç
    -0.06
    ክ
    -0.06
    .Create
    -0.06
    .GridColumn
    -0.06
    POSITIVE LOGITS
    .scalajs
    0.06
     offered
    0.06
    ﹣
    0.06
     sal
    0.06
     PCs
    0.06
    -linked
    0.06
     Fahr
    0.06
    试
    0.06
     POLIT
    0.06
    畢竟
    0.06
    Activations Density 0.081%

    No Known Activations