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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 7690
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kê
    -0.07
    erview
    -0.07
    榈
    -0.07
     pushes
    -0.07
     servers
    -0.07
    .vertical
    -0.07
     blessed
    -0.07
    抑え
    -0.06
    ɨ
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    的一种
    0.07
    .getRoot
    0.07
    读后感
    0.07
     "("
    0.07
    有一天
    0.07
    (eval
    0.07
    +=(
    0.07
     объ
    0.06
     Sampler
    0.06
    SAVE
    0.06
    Activations Density 0.050%

    No Known Activations