© 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. 89702
    Prev
    Next
    INDEX
    Explanations

    Diverse online text snippets

    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
     prest
    -0.07
    (database
    -0.07
     confinement
    -0.07
    (bus
    -0.06
    _network
    -0.06
     mnemonic
    -0.06
    (nome
    -0.06
    _acl
    -0.06
     shutdown
    -0.06
    _ns
    -0.06
    POSITIVE LOGITS
    ર
    0.07
    VertexUvs
    0.07
    .unlink
    0.07
    会产生
    0.07
    锧
    0.06
    三点
    0.06
    ⅀
    0.06
    rovers
    0.06
    洛杉
    0.06
     Exped
    0.06
    Activations Density 0.068%

    No Known Activations