INDEX

Explanations

hay

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

InstanceState

-0.29

æł¼æŀĹ

-0.29

une

-0.29

ogui

-0.29

outh

-0.28

antine

-0.27

UNE

-0.27

uth

-0.26

uten

-0.25

uder

-0.25

POSITIVE LOGITS

bable

0.28

leck

0.28

quÃŃ

0.27

fq

0.27

 Clippers

0.26

 detain

0.25

 Affairs

0.25

è¿ľç¦»

0.24

edt

0.24

haft

0.24

Activations Density 0.013%

hay

No Comments

No Known Activations