INDEX

Explanations

Read on

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

Bay

-0.29

Bay

-0.28

ces

-0.26

WEEN

-0.26

çĶŁçī©è´¨

-0.25

 oblig

-0.25

ÅŁÄ±

-0.25

 trail

-0.25

azon

-0.25

onas

-0.25

POSITIVE LOGITS

rÃ´

0.27

 consolidation

0.26

 headaches

0.24

(fr

0.24

åĽŀ

0.23

 Verb

0.23

å¤§è±¡

0.23

ĶåĽŀ

0.23

 surplus

0.23

 thugs

0.23

Activations Density 0.002%

Read on

No Comments

No Known Activations