© 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. 8236
    Prev
    Next
    INDEX
    Explanations

    for

    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
    Dar
    -0.07
     Flynn
    -0.07
    -death
    -0.06
    occer
    -0.06
     Coinbase
    -0.06
     hopping
    -0.06
    置身
    -0.06
    -body
    -0.06
    邮箱
    -0.06
    _run
    -0.06
    POSITIVE LOGITS
    要知道
    0.08
     celebrations
    0.07
     EXPER
    0.07
    With
    0.07
    既可以
    0.07
     leverage
    0.07
    documents
    0.06
    ?.
    0.06
    很多朋友
    0.06
    消费者的
    0.06
    Activations Density 0.001%

    No Known Activations