© 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. 27012
    Prev
    Next
    INDEX
    Explanations

    Software descriptions/disclaimers

    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
    被执行人
    -0.07
    兆
    -0.07
    iseconds
    -0.07
     people
    -0.07
    红利
    -0.07
    actly
    -0.06
    lian
    -0.06
     млн
    -0.06
    מכירות
    -0.06
    ");//
    -0.06
    POSITIVE LOGITS
     allowNull
    0.07
    עץ
    0.07
     Aws
    0.07
    严格的
    0.07
    _weights
    0.07
    /ne
    0.07
     sublime
    0.07
    +A
    0.07
     {};
↵
    0.07
    Tooltip
    0.07
    Activations Density 0.014%

    No Known Activations