© 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. 15-RESID-POST-AA
    11. 39492
    Prev
    Next
    INDEX
    Explanations

    interchange

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    耔
    -0.08
    📟
    -0.07
    .nasa
    -0.07
    rieb
    -0.07
     qos
    -0.07
    cade
    -0.07
    .plot
    -0.07
    _gettime
    -0.07
     VX
    -0.07
    わけです
    -0.06
    POSITIVE LOGITS
    cancel
    0.07
     "*
    0.07
     "
    0.07
    要进一步
    0.07
    ###↵↵
    0.07
    保密
    0.07
     """↵↵
    0.07
    留在
    0.07
     ");↵↵
    0.06
     choice
    0.06
    Activations Density 0.007%

    No Known Activations