INDEX

Explanations

.

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĩºå¤Ħ

-0.27

iverse

-0.25

clair

-0.25

æĤ²åĵĢ

-0.24

dap

-0.24

 historical

-0.23

irectional

-0.23

reb

-0.23

 RESP

-0.23

 continuity

-0.23

POSITIVE LOGITS

ä¼°è®¡

0.51

ä¼°ç®Ĺ

0.46

 estimates

0.45

 estimate

0.43

 Estimate

0.42

ä¼°

0.41

estimate

0.39

åħ¶ä¸Ńä¹ĭä¸Ģ

0.35

 Estimates

0.35

 estimated

0.35

Activations Density 0.004%

.

No Comments

No Known Activations