INDEX

Explanations

using/pausing

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

Approved

-0.28

jiang

-0.24

lee

-0.24

èĥ¶

-0.24

hua

-0.24

fare

-0.24

.BO

-0.24

.=

-0.24

æĥ³æ³ķ

-0.24

gÃ³

-0.24

POSITIVE LOGITS

 HttpHeaders

0.28

æĬ¥è®°èĢħ

0.25

bite

0.25

 accumulate

0.25

obbies

0.25

æľ¯

0.25

 accumulated

0.24

 increment

0.24

opleft

0.24

åĨħçļĦ

0.24

Activations Density 0.208%

using/pausing

No Comments

No Known Activations