© 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. 7-RESID-POST-AA
    11. 7497
    Prev
    Next
    INDEX
    Explanations

    Korean/Japanese

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _av
    -0.08
    lems
    -0.07
    ial
    -0.07
    专门为
    -0.07
    >"+↵
    -0.07
    ulado
    -0.07
    即使是
    -0.07
     earthquakes
    -0.06
    .concatenate
    -0.06
     deductible
    -0.06
    POSITIVE LOGITS
    难民
    0.07
    ADC
    0.06
    发热
    0.06
    Memory
    0.06
    树脂
    0.06
    Attachment
    0.06
     된
    0.06
    _mi
    0.06
    _players
    0.06
     sehen
    0.06
    Activations Density 0.002%

    No Known Activations