INDEX

Explanations

Geographical locations

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

éŃĤ

-0.27

åĲ¸çº³

-0.26

.setAuto

-0.26

Ð±ÑĢ

-0.26

hem

-0.25

çļĦå¢ŀéķ¿

-0.25

Spr

-0.25

_totals

-0.25

prung

-0.24

	Spring

-0.24

POSITIVE LOGITS

orate

0.26

æ±§

0.25

 monastery

0.25

 latin

0.25

ity

0.25

éĻĽ

0.25

æĸ¹åľĨ

0.25

ĳľ

0.25

(mon

0.24

ctica

0.24

Activations Density 0.006%

Geographical locations

No Comments

No Known Activations