INDEX

Explanations

method

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ftware

-0.28

 bootloader

-0.27

 boot

-0.27

harma

-0.26

moth

-0.25

boot

-0.25

 blink

-0.25

 Boot

-0.25

çĲħ

-0.24

/bg

-0.24

POSITIVE LOGITS

å¦ĥ

0.30

éĺĶ

0.28

 Verm

0.27

 Comparison

0.27

ej

0.26

 compar

0.25

vil

0.25

lij

0.25

å¥Ī

0.25

 REFERENCES

0.25

Activations Density 0.005%

method

No Comments

No Known Activations