© 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. 23-RESID-POST-AA
    11. 831
    Prev
    Next
    INDEX
    Explanations

    -selector

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /sign
    -0.08
     libro
    -0.07
     כסף
    -0.07
    登记
    -0.07
    getRoot
    -0.07
    	cm
    -0.07
    uger
    -0.07
     CREATE
    -0.06
    uelle
    -0.06
     taxing
    -0.06
    POSITIVE LOGITS
    печат
    0.08
     Elasticsearch
    0.07
     ebony
    0.07
     paragraphs
    0.07
     oscillator
    0.07
     keyboard
    0.07
    охран
    0.07
    !).
    0.07
    Hit
    0.07
     AppleWebKit
    0.07
    Activations Density 0.002%

    No Known Activations