INDEX

Explanations

Secret societies/esoteric knowledge

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

 manifold

-0.28

abra

-0.27

 Kurds

-0.26

åĲĦæĸ¹éĿ¢

-0.26

 Machine

-0.25

æīĭä¸Ĭ

-0.25

 machine

-0.24

 waterfront

-0.24

 decoded

-0.24

surname

-0.23

POSITIVE LOGITS

feito

0.28

`,

0.27

igest

0.27

æĶ¶

0.25

Ã³r

0.25

ä¸ľé£İ

0.25

ional

0.25

'",

0.25

 tunnels

0.24

*))

0.24

Activations Density 0.006%

Secret societies/esoteric knowledge

No Comments

No Known Activations