© 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. 15-RESID-POST-AA
    11. 49997
    Prev
    Next
    INDEX
    Explanations

    nil

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     microphone
    -0.07
    بحر
    -0.07
    admin
    -0.07
    מדריך
    -0.07
    ouden
    -0.07
    以习近平
    -0.07
     incontro
    -0.07
    גולשים
    -0.07
    corr
    -0.07
     ener
    -0.07
    POSITIVE LOGITS
    罢了
    0.07
     özgü
    0.07
     otros
    0.07
     sixty
    0.06
     unlawful
    0.06
     ousted
    0.06
     Betty
    0.06
    "])
    0.06
    仍旧
    0.06
     ellos
    0.06
    Activations Density 0.001%

    No Known Activations