INDEX

Explanations

specific references

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

Negative Logits

 spiral

-0.26

 husband

-0.25

reich

-0.25

 unfolded

-0.25

 fact

-0.24

 barrels

-0.24

datum

-0.23

 char

-0.23

fact

-0.23

 informal

-0.23

POSITIVE LOGITS

ç¦»

0.27

/problems

0.26

aea

0.26

é¦Ļèķī

0.25

lace

0.25

lia

0.25

PACE

0.25

laces

0.24

lashes

0.24

xFD

0.24

Activations Density 0.001%

specific references

No Known Activations