© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75865
    Prev
    Next
    INDEX
    Explanations

    1

    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
    INavigation
    -0.07
    bbe
    -0.07
    ﮡ
    -0.06
     בכ
    -0.06
    镄
    -0.06
    憧憬
    -0.06
     BRA
    -0.06
    失落
    -0.06
     PAL
    -0.06
     País
    -0.06
    POSITIVE LOGITS
     work
    0.08
    ,
↵
↵
    0.07
    .domain
    0.07
     aracı
    0.07
    qid
    0.07
    _in
    0.07
    qd
    0.07
     material
    0.07
    原因
    0.07
    作为
    0.07
    Activations Density 0.000%

    No Known Activations