© 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. 19-RESID-POST-AA
    11. 8098
    Prev
    Next
    INDEX
    Explanations

    bash

    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
    .Hidden
    -0.08
    轩
    -0.07
     tcp
    -0.07
     עסק
    -0.07
    农场
    -0.07
     LONG
    -0.07
    _sec
    -0.07
    菠
    -0.07
    reads
    -0.07
    side
    -0.07
    POSITIVE LOGITS
    ゾ
    0.07
     Donate
    0.07
    Џ
    0.07
     gratuita
    0.07
    ![
    0.07
    记者从
    0.06
    Yii
    0.06
     сиг
    0.06
     Kits
    0.06
    一如既
    0.06
    Activations Density 0.001%

    No Known Activations