© 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. 68975
    Prev
    Next
    INDEX
    Explanations

    Math and calculations

    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
     modified
    -0.07
    Once
    -0.07
     matrices
    -0.07
    镧
    -0.07
    extended
    -0.07
    瘭
    -0.07
    球
    -0.06
    ugged
    -0.06
    soft
    -0.06
    unciation
    -0.06
    POSITIVE LOGITS
     pouvoir
    0.07
    的压力
    0.07
     �
    0.07
    急速
    0.07
    /im
    0.07
    MLElement
    0.07
    _CALL
    0.06
    _INIT
    0.06
    _ssh
    0.06
    上看
    0.06
    Activations Density 0.009%

    No Known Activations