© 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. 61446
    Prev
    Next
    INDEX
    Explanations

    On

    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
     Partition
    -0.08
     were
    -0.07
     indul
    -0.07
    摄
    -0.07
     Larger
    -0.07
    攝
    -0.07
    ログ
    -0.07
     Guest
    -0.06
    เสร
    -0.06
    атель
    -0.06
    POSITIVE LOGITS
     relev
    0.07
    blocking
    0.07
    챦
    0.07
     kd
    0.07
     WaitForSeconds
    0.07
    天空
    0.07
    额头
    0.06
    캄
    0.06
     jakiś
    0.06
     księ
    0.06
    Activations Density 0.026%

    No Known Activations