© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 58631
    Prev
    Next
    INDEX
    Explanations

    antibiotics

    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
    aligned
    -0.07
    ervation
    -0.07
    𝘞
    -0.07
    😑
    -0.07
    占地面积
    -0.07
     prevents
    -0.07
    Whats
    -0.06
    然
    -0.06
    一刻
    -0.06
    𝘀
    -0.06
    POSITIVE LOGITS
     constructive
    0.08
     amor
    0.08
     iov
    0.07
     switched
    0.07
    staff
    0.07
     superintendent
    0.06
     האחרונה
    0.06
     STDERR
    0.06
     organiz
    0.06
     prostitutas
    0.06
    Activations Density 0.053%

    No Known Activations