INDEX

Explanations

atomic

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

hole

-0.25

inkle

-0.25

scope

-0.24

 bÃŃ

-0.24

.Validation

-0.24

enco

-0.23

adora

-0.23

ani

-0.23

flower

-0.23

å³Ĵ

-0.23

POSITIVE LOGITS

pheres

0.27

 ÑĦÐ¸Ð½

0.27

ä¹ī

0.25

æ®µ

0.25

èłĸ

0.25

kal

0.25

 leth

0.24

èĤĦ

0.24

empl

0.24

æ®ĸ

0.24

Activations Density 0.002%

atomic

No Comments

No Known Activations