INDEX

Explanations

Location prepositions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

smtp

-0.27

ĽĦ

-0.27

éķ¿çŁŃ

-0.26

 stuffing

-0.26

.sy

-0.25

å¡«

-0.24

 motives

-0.24

éĩĮçļĦ

-0.24

kra

-0.24

 meant

-0.23

POSITIVE LOGITS

Ont

0.33

cheme

0.28

oney

0.27

Ont

0.27

eton

0.26

ont

0.26

/off

0.26

è½½

0.26

Ã´n

0.26

 scen

0.25

Activations Density 0.011%

Location prepositions

No Comments

No Known Activations