INDEX

Explanations

positive sentiment

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

 Unity

-0.26

')?>

-0.25

ktop

-0.24

leted

-0.24

adier

-0.24

èĢ³

-0.24

ih

-0.24

 spre

-0.24

 division

-0.23

 mote

-0.23

POSITIVE LOGITS

ahun

0.28

 liá»ĩt

0.27

èµ°å¾Ĺ

0.27

ropri

0.26

 Falls

0.25

ãģĤãģ¨

0.25

itude

0.25

nhi

0.25

 autofocus

0.25

 AppState

0.24

Activations Density 0.004%

positive sentiment

No Comments

No Known Activations