INDEX

Explanations

and

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

è°ħ

-0.28

.SOCK

-0.27

IBC

-0.27

Ipv

-0.26

qua

-0.26

LAST

-0.25

ãĥĿãĥ¼ãĥĪ

-0.25

_IPV

-0.24

 Pent

-0.24

_svc

-0.24

POSITIVE LOGITS

 Heck

0.28

ahn

0.27

çīĮ

0.26

 vulgar

0.26

åĩºæīĭ

0.25

.wind

0.25

 coursework

0.25

éĩįåº¦

0.25

 regions

0.24

 Accent

0.24

Activations Density 0.010%

and

No Comments

No Known Activations