© 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. 71018
    Prev
    Next
    INDEX
    Explanations

    scientific journal articles

    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
     temptation
    -0.07
    MMdd
    -0.07
    ываем
    -0.07
     예수님
    -0.07
    Подроб
    -0.07
    過程中
    -0.07
     IPP
    -0.06
     الإنسان
    -0.06
    חלום
    -0.06
     btnSave
    -0.06
    POSITIVE LOGITS
    _corners
    0.07
    �
    0.07
    _workers
    0.07
     quant
    0.07
    勋
    0.07
    =$
    0.07
    빅
    0.07
    ALE
    0.07
    SR
    0.07
     matching
    0.07
    Activations Density 0.020%

    No Known Activations