© 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. 22524
    Prev
    Next
    INDEX
    Explanations

    IEEE journal articles

    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
    Dis
    -0.07
    屐
    -0.06
    ried
    -0.06
    Full
    -0.06
    Ɓ
    -0.06
    踹
    -0.06
     fully
    -0.06
    vidence
    -0.06
    South
    -0.06
    Ended
    -0.06
    POSITIVE LOGITS
    نامج
    0.08
    急于
    0.07
     necesario
    0.07
    וקר
    0.07
     relaciones
    0.07
     Salesforce
    0.07
     האחר
    0.07
     Greatest
    0.07
    一个新的
    0.07
     necesita
    0.07
    Activations Density 0.001%

    No Known Activations