INDEX

Explanations

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Deployment

-0.28

Overview

-0.28

æŁ¥çľĭåħ¨æĸĩ

-0.26

_IE

-0.25

åĨħåĪĨæ³Į

-0.25

 diapers

-0.24

hesion

-0.24

modity

-0.24

 deployment

-0.24

 Roller

-0.23

POSITIVE LOGITS

è´¨éĩıåĴĮ

0.34

 onError

0.26

mont

0.26

 proportional

0.26

 warned

0.25

onas

0.25

olen

0.25

lig

0.25

 QUAL

0.25

çī

0.25

Activations Density 0.002%

code

No Comments

No Known Activations