© 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. 15-RESID-POST-AA
    11. 11204
    Prev
    Next
    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    흄
    -0.07
    десь
    -0.07
    比利
    -0.07
    领导者
    -0.07
    <N
    -0.07
    ⑅
    -0.07
    .annot
    -0.07
     נשמע
    -0.07
    푀
    -0.06
    <?
    -0.06
    POSITIVE LOGITS
    .ImageField
    0.07
     overcrow
    0.07
    ificance
    0.07
    סכום
    0.07
     crises
    0.07
    melon
    0.07
    Extent
    0.07
    arov
    0.07
    roken
    0.06
    sections
    0.06
    Activations Density 0.083%

    No Known Activations