INDEX

Explanations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

laps

-0.30

issen

-0.27

 prefers

-0.25

inite

-0.25

åİĭæĬĳ

-0.25

 prefer

-0.25

ionales

-0.25

 inconvenient

-0.24

èĻ¢

-0.24

bury

-0.24

POSITIVE LOGITS

 constructor

0.27

_each

0.26

å¸ĮæľĽèĩªå·±

0.26

ear

0.26

&(

0.25

 Tara

0.24

é«ĺçº§

0.24

ç§¯æŀģéħįåĲĪ

0.24

pe

0.24

constructor

0.24

Activations Density 0.005%

advertisements

No Comments

No Known Activations