© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 52184
    Prev
    Next
    INDEX
    Explanations

    laws and protests

    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
    これまで
    -0.08
     sequencing
    -0.07
    HeaderInSection
    -0.07
    شهد
    -0.06
    慆
    -0.06
    (fields
    -0.06
    	unsigned
    -0.06
    UNC
    -0.06
    询问
    -0.06
     halluc
    -0.06
    POSITIVE LOGITS
     bom
    0.09
    +");↵
    0.07
     comb
    0.07
    representation
    0.07
    топ
    0.07
    ")){
↵
    0.07
    ktion
    0.07
    拓
    0.07
    طب
    0.07
     theor
    0.07
    Activations Density 0.031%

    No Known Activations