INDEX

Explanations

R

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Ø§ÙĦØŃÙĬ

-0.27

(reinterpret

-0.26

æ¤ħ

-0.26

rer

-0.26

 Operating

-0.25

æĪĺåıĭ

-0.25

æĶ¹è£ħ

-0.24

Dynamic

-0.24

 Dynamic

-0.24

/ag

-0.24

POSITIVE LOGITS

 softened

0.25

ernes

0.25

ials

0.25

 look

0.25

èĤĭ

0.25

uada

0.24

armed

0.24

æıĨ

0.24

metic

0.24

ryn

0.24

Activations Density 0.093%

R

No Comments

No Known Activations