© 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. 23-RESID-POST-AA
    11. 575
    Prev
    Next
    INDEX
    Explanations

    intended use and consequences

    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
    =item
    -0.07
    o
    -0.07
    �
    -0.06
    抽取
    -0.06
    Ljava
    -0.06
    ensis
    -0.06
    <Address
    -0.06
    收集
    -0.06
    asonic
    -0.06
    .top
    -0.06
    POSITIVE LOGITS
     нек
    0.07
    abbreviation
    0.07
    ザ
    0.07
     filmm
    0.07
    пут
    0.07
     />↵
    0.07
     illust
    0.07
    regon
    0.07
    думать
    0.07
    ं
    0.07
    Activations Density 0.002%

    No Known Activations