© 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. 19-RESID-POST-AA
    11. 70968
    Prev
    Next
    INDEX
    Explanations

    enzyme lodash

    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
    发明专利
    -0.08
    �
    -0.07
    藓
    -0.07
     Bürger
    -0.07
    חליף
    -0.07
    ភ
    -0.07
    端午
    -0.07
     Habitat
    -0.07
    .generic
    -0.07
     Become
    -0.06
    POSITIVE LOGITS
     ford
    0.07
     mpg
    0.07
    hes
    0.07
    实际
    0.07
    _sched
    0.07
    最少
    0.07
    深
    0.07
     lowest
    0.07
    itung
    0.07
     Meng
    0.06
    Activations Density 0.001%

    No Known Activations