© 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 EvalsExportsAPI 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. 85717
    Prev
    Next
    INDEX
    Explanations

    mean

    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
    โซ
    -0.07
    anon
    -0.07
     cris
    -0.07
    ᵀ
    -0.07
    JA
    -0.07
     "*.
    -0.06
     �
    -0.06
     Hd
    -0.06
     cancelButtonTitle
    -0.06
    ("(
    -0.06
    POSITIVE LOGITS
     receptor
    0.08
    水稻
    0.07
     Swedish
    0.07
     debacle
    0.07
    igion
    0.07
    attering
    0.07
     décembre
    0.07
     destroyer
    0.07
     Giants
    0.07
    ividad
    0.07
    Activations Density 0.003%

    No Known Activations