© 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. 110325
    Prev
    Next
    INDEX
    Explanations

    forward/backward slash or pipe

    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
    zę
    -0.07
    haul
    -0.07
    箜
    -0.07
    pler
    -0.07
     bağl
    -0.07
     GPL
    -0.06
    append
    -0.06
     hung
    -0.06
    两次
    -0.06
     בגלל
    -0.06
    POSITIVE LOGITS
    -offsetof
    0.07
    崽
    0.07
     strengths
    0.07
    	us
    0.07
    提现
    0.07
     gestion
    0.07
     properties
    0.07
     stag
    0.07
    ustry
    0.06
    	camera
    0.06
    Activations Density 0.002%

    No Known Activations