INDEX

Explanations

code/copyright/system logs

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

WARD

-0.27

agner

-0.27

ward

-0.27

 Yong

-0.27

kke

-0.27

åħīæĺİ

-0.27

etri

-0.26

lijk

-0.25

etes

-0.25

èµ¶

-0.25

POSITIVE LOGITS

å¹´ä¹ĭ

0.27

 approx

0.27

.esp

0.26

èİ·å¾ĹæĦŁ

0.26

/weather

0.26

 resolve

0.25

resolution

0.25

 resolution

0.25

èĢĹè´¹

0.25

 Banks

0.24

Activations Density 0.010%

code/copyright/system logs

No Comments

No Known Activations