© 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. 108954
    Prev
    Next
    INDEX
    Explanations

    network connections

    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
    夙
    -0.07
    集市
    -0.07
     Vista
    -0.07
    óa
    -0.07
     has
    -0.07
     MAN
    -0.07
    обав
    -0.06
     catering
    -0.06
     napraw
    -0.06
    太极拳
    -0.06
    POSITIVE LOGITS
    @@
    0.07
    Objects
    0.07
     ###↵
    0.07
    Locale
    0.07
    .getProject
    0.07
    интерес
    0.06
    _empty
    0.06
    .cfg
    0.06
    Getter
    0.06
    ⋮
    0.06
    Activations Density 0.030%

    No Known Activations