INDEX

Explanations

scientific texts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.createFrom

-0.29

ukkan

-0.27

oodle

-0.27

ettel

-0.27

enthal

-0.26

fuse

-0.25

éĺ³åİ¿

-0.25

rompt

-0.24

heid

-0.24

ilden

-0.24

POSITIVE LOGITS

boards

0.26

çļĦä½ľçĶ¨

0.24

 incon

0.24

Repair

0.24

çĨ¬

0.24

 Verify

0.23

ç²³

0.23

å¸¸å¹´

0.23

references

0.23

tails

0.23

Activations Density 1.207%

scientific texts

No Comments

No Known Activations