INDEX

Explanations

Dates/Date-related

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 Harmon

-0.26

Har

-0.26

åĳĵ

-0.25

.SOCK

-0.25

 consistent

-0.24

 Theory

-0.24

@js

-0.24

 Thought

-0.24

EFR

-0.24

åı°ä¸Ĭ

-0.24

POSITIVE LOGITS

pin

0.30

Rep

0.28

Take

0.25

rep

0.25

åĬ³

0.25

rep

0.25

obody

0.25

çĸļ

0.25

msgs

0.24

interval

0.24

Activations Density 0.048%

Dates/Date-related

No Comments

No Known Activations