Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 115249
    Prev
    Next
    INDEX
    Explanations

    Summary

    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
    Cheap
    -0.09
    tty
    -0.07
     Seamless
    -0.07
     Recursive
    -0.07
     Huffington
    -0.07
    研制
    -0.07
    代言人
    -0.07
    	Toast
    -0.07
    dns
    -0.07
    :e
    -0.07
    POSITIVE LOGITS
    _POSTFIELDS
    0.08
    馐
    0.07
     Stück
    0.07
    (pid
    0.07
    quoted
    0.07
     emlrt
    0.06
     builder
    0.06
    arshal
    0.06
     decency
    0.06
    SpecWarn
    0.06
    Activations Density 0.001%

    No Known Activations