INDEX

Explanations

Mol

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SOURCE

-0.28

à¸ĵà¸²

-0.26

UCH

-0.25

åħ¨æł¡

-0.25

ereotype

-0.25

.Evaluate

-0.25

 SOURCE

-0.25

éĿĵ

-0.24

å¼Ģåħ·

-0.24

ä¾Ŀæ¬¡

-0.24

POSITIVE LOGITS

æĬ¼

0.28

Ð¼Ð°Ð½

0.28

INO

0.26

oser

0.26

grades

0.26

miss

0.26

remium

0.25

adal

0.25

 Equip

0.25

çł»

0.25

Activations Density 0.613%

Mol

No Comments

No Known Activations