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. 23-RESID-POST-AA
    6. 130199
    Prev
    Next
    INDEX
    Explanations

    say "for"

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    楯
    -0.07
    .getBean
    -0.07
     Denied
    -0.07
    Dallas
    -0.07
     Measurement
    -0.07
    .Sound
    -0.07
     Rahmen
    -0.07
    .gz
    -0.07
     invites
    -0.07
    ]<
    -0.07
    POSITIVE LOGITS
    ƞ
    0.07
     Totally
    0.07
    policy
    0.06
    𡐓
    0.06
     avoir
    0.06
    𝓞
    0.06
    bones
    0.06
     toastr
    0.06
    trace
    0.06
     associations
    0.06
    Activations Density 0.029%

    No Known Activations